© 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. 19-RESID-POST-AA
    11. 74014
    Prev
    Next
    INDEX
    Explanations

    Mitchell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ᛅ
    -0.09
     addr
    -0.07
     establishing
    -0.07
     poner
    -0.07
     sustaining
    -0.07
    以至于
    -0.07
     достиг
    -0.07
     affection
    -0.07
     Explicit
    -0.07
     debacle
    -0.07
    POSITIVE LOGITS
     Codes
    0.07
    .NONE
    0.07
    工作站
    0.07
    فيدي
    0.07
    图
    0.06
    #plt
    0.06
    UNS
    0.06
    谈
    0.06
    /cc
    0.06
     legion
    0.06
    Activations Density 0.028%

    No Known Activations