© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8675
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sustaining
    -0.27
     aiding
    -0.27
     gent
    -0.27
    ent
    -0.27
     maintaining
    -0.26
     deep
    -0.26
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.26
    ations
    -0.26
    ç»´æĬ¤
    -0.25
     sustain
    -0.25
    POSITIVE LOGITS
    andel
    0.28
    ä¸Ģæľ¬ä¹¦
    0.27
    idon
    0.27
    解æĶ¾
    0.26
    ä»Ģ
    0.26
    adol
    0.25
    hei
    0.25
    enqueue
    0.25
    wat
    0.25
    .Dispatch
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.