© 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. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38924
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹ĪæĦıæĢĿ
    -0.33
     Remark
    -0.29
     ward
    -0.27
    ä¸ŃåĽ½åĪ¶éĢł
    -0.26
     Strike
    -0.26
    ildo
    -0.25
    å°º
    -0.25
     Ward
    -0.24
    翼
    -0.24
     rz
    -0.24
    POSITIVE LOGITS
    :host
    0.27
    é«ĺ涨
    0.27
    nton
    0.25
    braco
    0.25
    è¿ģ
    0.25
     Bradford
    0.25
    渴
    0.24
     "'.
    0.24
     canon
    0.24
    pone
    0.23
    Activations Density 64.613%

    No Known Activations

    This feature has no known activations.