© 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. 30-TRANSCODER-HP
    7. 95267
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roys
    -0.28
    åĪº
    -0.26
    tÃł
    -0.26
    board
    -0.26
    cean
    -0.25
    BODY
    -0.25
     funded
    -0.25
     Bew
    -0.25
     Birch
    -0.25
     hugged
    -0.24
    POSITIVE LOGITS
    çī¡ä¸¹
    0.27
    actics
    0.27
    addle
    0.27
    patial
    0.27
    ubi
    0.26
    COORD
    0.26
    èĢĴ
    0.25
     operation
    0.24
    åIJĪéĢĤçļĦ
    0.24
    åIJĪçIJĨçļĦ
    0.24
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.