© 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. 108448
    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
    richt
    -0.30
    廪
    -0.27
    lite
    -0.27
    amber
    -0.27
    iot
    -0.26
    ç§ĴéĴŁ
    -0.26
    å¥Ĺ
    -0.25
    åŀĭä¼ģä¸ļ
    -0.25
    laus
    -0.25
    etti
    -0.25
    POSITIVE LOGITS
     det
    0.29
    DET
    0.29
    agedList
    0.27
     Det
    0.26
     GIVEN
    0.25
    -det
    0.25
    ipur
    0.25
     OCC
    0.25
    ActionCreators
    0.25
    çļĦæĥħåĨµä¸ĭ
    0.25
    Activations Density 8.424%

    No Known Activations

    This feature has no known activations.