© 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 EvalsExportsAPI 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. 74570
    Prev
    Next
    INDEX
    Explanations

    instructions and information about accessing healthcare services, seeking medical advice, and deciding between emergency and non‑emergency care

    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
    ==-
    -0.07
     Nolan
    -0.07
     founded
    -0.07
     проис
    -0.07
    占地面积
    -0.07
     indef
    -0.07
     Lam
    -0.07
     Cob
    -0.07
    vod
    -0.07
    Купить
    -0.07
    POSITIVE LOGITS
    .JWT
    0.08
    addField
    0.07
    _PAGES
    0.07
    ˝
    0.07
     מא
    0.07
    爿
    0.07
    _MIX
    0.07
    .'</
    0.07
    �
    0.07
    文物
    0.07
    Activations Density 0.034%

    No Known Activations