© 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. 3928
    Prev
    Next
    INDEX
    Explanations

    News snippets

    np_max-act · gemini-2.0-flash

    the start-of-assistant turn marker in chat-style formatted transcripts (i.e., the assistant role boundary token).

    oai_token-act-pair · gpt-5Triggered 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
     Krishna
    -0.08
    (weather
    -0.08
    .connected
    -0.07
    Strict
    -0.07
    _appro
    -0.07
    oph
    -0.07
    .Login
    -0.07
    (This
    -0.07
    .Aggressive
    -0.07
    摧
    -0.07
    POSITIVE LOGITS
     Entwicklung
    0.08
    拖欠
    0.07
    .Future
    0.07
    emie
    0.07
     Portal
    0.06
    young
    0.06
     bru
    0.06
    人选
    0.06
    灶
    0.06
    别说
    0.06
    Activations Density 0.133%

    No Known Activations