Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 31173
    Prev
    Next
    INDEX
    Explanations

    Recycling/Donations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GetName
    -0.07
     إن
    -0.07
    -el
    -0.07
     Universidad
    -0.07
     likes
    -0.07
    פארק
    -0.07
     daher
    -0.06
    个体
    -0.06
     Ele
    -0.06
     أفضل
    -0.06
    POSITIVE LOGITS
    yl
    0.07
    GM
    0.07
    뮤
    0.06
    Return
    0.06
    ᛚ
    0.06
    玡
    0.06
    Craig
    0.06
    /at
    0.06
    _SECRET
    0.06
    RAY
    0.06
    Activations Density 0.012%

    No Known Activations