© 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. 140876
    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
    Not in Any Lists

    No Comments

    Negative Logits
     forever
    -0.27
     flown
    -0.25
     Estimate
    -0.25
    éŃĶæľ¯
    -0.24
    cake
    -0.24
     Bet
    -0.24
    èĽĭç³ķ
    -0.24
    await
    -0.24
     Patton
    -0.23
    åľ°è´¨
    -0.23
    POSITIVE LOGITS
    ä¸įåIJĪéĢĤ
    0.28
    é¦ĸåıij
    0.28
    propri
    0.28
    .nlm
    0.27
    第ä¸Ģæī¹
    0.27
    inding
    0.26
     restrictions
    0.26
    dings
    0.25
    restriction
    0.24
    -initial
    0.23
    Activations Density 6.082%

    No Known Activations

    This feature has no known activations.