© 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. 95775
    Prev
    Next
    INDEX
    Explanations

    {

    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
    临近
    -0.07
    表格
    -0.06
    ובר
    -0.06
     anybody
    -0.06
     fitness
    -0.06
    allest
    -0.06
    一个是
    -0.06
     finde
    -0.06
     Alleg
    -0.06
    返
    -0.06
    POSITIVE LOGITS
    &S
    0.07
    .jboss
    0.07
    聘
    0.07
    /dom
    0.07
     sim
    0.07
    _PUT
    0.07
    общи
    0.07
    رات
    0.07
     SCT
    0.06
    �
    0.06
    Activations Density 0.012%

    No Known Activations