© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 126742
    Prev
    Next
    INDEX
    Explanations

    relationships and dating

    np_max-act · gemini-2.0-flash

    Words and phrases referring to romantic partners, relationship status, milestones, and commitment (boyfriend/girlfriend/partner, exclusivity, duration, relationship).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rico
    -0.07
     opponent
    -0.07
    .in
    -0.06
     cuenta
    -0.06
     נית
    -0.06
    예
    -0.06
    ñe
    -0.06
    JUST
    -0.06
    inee
    -0.06
    وز
    -0.06
    POSITIVE LOGITS
     &$
    0.08
     habits
    0.07
     דואר
    0.07
    egr
    0.07
    保养
    0.07
    `.`
    0.07
    מול
    0.07
     "&#
    0.07
    .setLayoutManager
    0.06
    ⛱
    0.06
    Activations Density 0.061%

    No Known Activations