© 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. 11-RESID-POST-AA
    11. 28484
    Prev
    Next
    INDEX
    Explanations

    creativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    供水
    -0.06
    _Return
    -0.06
    oden
    -0.06
    кан
    -0.06
    inha
    -0.06
     Online
    -0.06
    וצג
    -0.06
    ivos
    -0.06
     enable
    -0.06
    Thinking
    -0.06
    POSITIVE LOGITS
    战友
    0.08
    ;padding
    0.07
    쌍
    0.07
     роман
    0.07
     năm
    0.07
    %"
    0.07
    浓厚
    0.07
    Dam
    0.07
    ][]
    0.07
     bệnh
    0.07
    Activations Density 0.049%

    No Known Activations