© 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. 30-TRANSCODER-HP
    7. 95261
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ŀåľ°
    -0.30
     Hait
    -0.29
    ç¼İ
    -0.28
    ç»ĩ
    -0.26
    éĽĨ
    -0.26
    è¯ī
    -0.25
     wand
    -0.25
     colonial
    -0.25
     equal
    -0.24
     cuisine
    -0.24
    POSITIVE LOGITS
    icot
    0.30
    æĮ
    0.29
    anford
    0.28
     indemn
    0.26
    _VOID
    0.25
    åħ¥åºĵ
    0.25
    ÇĶ
    0.25
     anders
    0.24
    lasses
    0.24
    nos
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.