© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 83401
    Prev
    Next
    INDEX
    Explanations

    disclaimers

    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
    Negative Logits
    Suc
    -0.08
    全覆盖
    -0.07
     passed
    -0.07
    槚
    -0.07
     spp
    -0.07
    ĥ
    -0.07
    绁
    -0.06
    Ā
    -0.06
    雾霾
    -0.06
    켈
    -0.06
    POSITIVE LOGITS
    尤其是
    0.07
    _dept
    0.07
    ษา
    0.07
    porter
    0.07
     PCB
    0.07
    (pages
    0.07
    Renderer
    0.07
    .Panel
    0.07
     يحدث
    0.07
    -profit
    0.07
    Activations Density 0.013%

    No Known Activations