© 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. 71776
    Prev
    Next
    INDEX
    Explanations

    activated

    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
    存在问题
    -0.07
     יור
    -0.07
    ⊆
    -0.07
     archival
    -0.07
    年薪
    -0.07
    执教
    -0.07
    路线
    -0.06
    绗
    -0.06
     Tory
    -0.06
    各项工作
    -0.06
    POSITIVE LOGITS
    _OLD
    0.07
    'aff
    0.07
    svg
    0.07
    ’in
    0.06
    -small
    0.06
    alam
    0.06
    luck
    0.06
    .utility
    0.06
    posix
    0.06
    决定
    0.06
    Activations Density 0.001%

    No Known Activations