© 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. 127963
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,strlen
    -0.07
     Temporary
    -0.07
    此次
    -0.07
    uve
    -0.07
    먮
    -0.07
    =sub
    -0.06
    _sig
    -0.06
    ⏜
    -0.06
    說明
    -0.06
    tp
    -0.06
    POSITIVE LOGITS
     Shader
    0.07
     الألم
    0.07
     phenomen
    0.07
     blender
    0.07
    .optimize
    0.07
     Fat
    0.07
     deferred
    0.06
    blend
    0.06
    .Interfaces
    0.06
    奥巴马
    0.06
    Activations Density 0.360%

    No Known Activations