© 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. 40405
    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
     Division
    -0.33
     Reform
    -0.32
     CrossRef
    -0.31
     Conf
    -0.30
     Quadr
    -0.30
    (uint
    -0.29
     County
    -0.29
     uint
    -0.28
     Virt
    -0.28
     Vice
    -0.28
    POSITIVE LOGITS
    culate
    0.30
    ä¸ĢæĿ¡
    0.28
    ä¸Ģ次
    0.28
    æľĢæľī
    0.27
    第ä¸ĢæĿ¡
    0.27
     latest
    0.26
    åħ¬å¼Ģåıijè¡Į
    0.26
    ắp
    0.26
    alic
    0.26
    ä¸Ģç«Ļå¼ı
    0.26
    Activations Density 0.185%

    No Known Activations

    This feature has no known activations.