© 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. 97062
    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
    Negative Logits
    å¶Ĥ
    -0.24
     Imam
    -0.24
     Nobody
    -0.23
    é¹Ħ
    -0.22
    æħ¢æħ¢åľ°
    -0.21
    第ä¸Ģ书记
    -0.21
     sợ
    -0.21
    cad
    -0.21
    åħļå§Ķ书记
    -0.21
     Implement
    -0.21
    POSITIVE LOGITS
    velt
    0.25
    subtype
    0.23
    ationToken
    0.22
    onacci
    0.22
    TINGS
    0.22
    ems
    0.22
    orus
    0.22
     visuals
    0.21
    :`~
    0.21
    ElementsBy
    0.21
    Activations Density 0.968%

    No Known Activations

    This feature has no known activations.