© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 86661
    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
    𝙇
    -0.08
    各项工作
    -0.07
     מאות
    -0.07
    毛
    -0.07
    zl
    -0.07
     importantly
    -0.07
    (SQL
    -0.07
     자체
    -0.07
     Dion
    -0.06
    QtCore
    -0.06
    POSITIVE LOGITS
    annon
    0.07
    //
    0.07
    .metamodel
    0.07
     Fuse
    0.07
    .user
    0.07
    _PF
    0.07
    舌尖
    0.07
     Buyer
    0.06
    conscious
    0.06
    招股书
    0.06
    Activations Density 0.025%

    No Known Activations