© 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. 142437
    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
     placeholders
    -0.32
    ACLE
    -0.28
    oge
    -0.27
    ạch
    -0.26
     placeholder
    -0.26
     subscript
    -0.26
    ifi
    -0.25
     slack
    -0.25
    Ä¡
    -0.25
     overt
    -0.25
    POSITIVE LOGITS
     reunited
    0.29
    tu
    0.28
     Stereo
    0.27
    SFML
    0.26
    è¿ĺæĺ¯
    0.25
    å«Įçĸij
    0.25
    ucs
    0.24
    ä¸ĵè¾ij
    0.24
    éªĿ
    0.24
     confiscated
    0.24
    Activations Density 0.815%

    No Known Activations

    This feature has no known activations.