© 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. 20-TRANSCODER-HP
    7. 142768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç»ĵç®Ĺ
    -0.28
    æĸ¹ä¾¿
    -0.26
     credit
    -0.26
    inct
    -0.25
     ili
    -0.25
    comb
    -0.25
    ps
    -0.25
     convenience
    -0.25
    ibus
    -0.25
    宾
    -0.24
    POSITIVE LOGITS
    ÑĥлÑĮ
    0.26
    åĵªéĩĮ
    0.25
    æŁĵ
    0.25
    SpaceItem
    0.25
    ÂŃt
    0.25
    碰
    0.24
    åħij
    0.24
    Touches
    0.24
    èį¯ä¸ļ
    0.24
    воÑĢоÑĤ
    0.24
    Activations Density 1.785%

    No Known Activations

    This feature has no known activations.