© 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. 106872
    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
    çĸµ
    -0.28
    ä¸Ģæĸ¹éĿ¢
    -0.26
    IDES
    -0.26
    ä¸įæĸŃæī©å¤§
    -0.25
    .inspect
    -0.25
     mù
    -0.25
    ENDOR
    -0.24
     tÆ°á»Łng
    -0.24
    (tv
    -0.24
    ycz
    -0.24
    POSITIVE LOGITS
     conven
    0.29
     collo
    0.26
    ä¸ĸä¿Ĺ
    0.26
    æµģè¡Į
    0.26
    缼
    0.25
    é¢Ĩ
    0.25
    æľīè¿ĩ
    0.25
     neutrality
    0.24
    uler
    0.24
    å®Įå¤ĩ
    0.24
    Activations Density 46.175%

    No Known Activations

    This feature has no known activations.