© 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. 19-RESID-POST-AA
    11. 70430
    Prev
    Next
    INDEX
    Explanations

    violating rules/boundaries

    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
     NHS
    -0.07
    .kafka
    -0.07
    铯
    -0.07
     כלי
    -0.07
    isempty
    -0.07
    祉
    -0.07
    Unix
    -0.07
     Алексан
    -0.07
     unix
    -0.07
    uv
    -0.06
    POSITIVE LOGITS
    Inverse
    0.08
    ()]↵
    0.08
    调查
    0.07
    天鹅
    0.07
    .navigationItem
    0.07
    \E
    0.07
     tightly
    0.07
    这里
    0.07
    偶
    0.07
     resc
    0.07
    Activations Density 0.001%

    No Known Activations