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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 59516
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    TypeID
    -0.07
     PageInfo
    -0.07
     leave
    -0.06
    חינוך
    -0.06
    .ACT
    -0.06
     FRE
    -0.06
    _SETTING
    -0.06
     STILL
    -0.06
     Frid
    -0.06
     Ot
    -0.06
    POSITIVE LOGITS
     charm
    0.07
     Slow
    0.07
    なんと
    0.07
    软
    0.07
    躲在
    0.07
     recur
    0.06
    鏈
    0.06
    urrences
    0.06
    阀
    0.06
    阻挡
    0.06
    Activations Density 0.012%

    No Known Activations