© 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. 64566
    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
    LIKELY
    -0.31
    礼
    -0.26
    KI
    -0.25
    |-
    -0.25
     deaf
    -0.24
     compensation
    -0.24
     archival
    -0.24
    ä¸į满
    -0.24
     _.
    -0.23
    ÂŃi
    -0.23
    POSITIVE LOGITS
    erva
    0.28
    oped
    0.27
    ãģ¾ãĤĭ
    0.26
    è·¯
    0.25
    zers
    0.25
    .indices
    0.25
    nung
    0.25
    heads
    0.25
    Indices
    0.24
    chez
    0.24
    Activations Density 18.397%

    No Known Activations

    This feature has no known activations.