© 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. 38736
    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
    Negative Logits
    æĮĤåľ¨
    -0.28
    被æī§è¡Į
    -0.28
    被
    -0.27
    并ä¸İ
    -0.27
    FINITY
    -0.26
     Auss
    -0.26
    imes
    -0.26
    ena
    -0.25
     rempl
    -0.25
     '\''
    -0.25
    POSITIVE LOGITS
    &w
    0.27
    ocracy
    0.26
    /errors
    0.25
     costing
    0.25
     Toolbox
    0.24
    leases
    0.24
     Hod
    0.24
    æĪ·ç±į
    0.24
    0.24
     Moff
    0.23
    Activations Density 13.898%

    No Known Activations

    This feature has no known activations.