© 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. 27964
    Prev
    Next
    INDEX
    Explanations

    "<"

    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
    леж
    -0.07
     CT
    -0.06
    液晶
    -0.06
    赴
    -0.06
    _PTR
    -0.06
    Penn
    -0.06
    쉡
    -0.06
    뎬
    -0.06
    社區
    -0.06
     nit
    -0.06
    POSITIVE LOGITS
    iya
    0.07
     scrollbar
    0.07
    カップ
    0.07
    谎言
    0.07
    dae
    0.07
     Thông
    0.07
    ⌧
    0.06
     Champion
    0.06
     phút
    0.06
    _district
    0.06
    Activations Density 0.002%

    No Known Activations