© 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. 8747
    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
     Rodrig
    -0.27
    +-
    -0.25
     Cellular
    -0.25
    å©ļ
    -0.25
    ูล
    -0.25
    '>$
    -0.24
    scanner
    -0.24
    ë§Ŀ
    -0.24
    $log
    -0.24
    éĩİçĶŁ
    -0.23
    POSITIVE LOGITS
     Perkins
    0.28
    nds
    0.25
     inequalities
    0.25
    èĸ®
    0.25
    壤
    0.24
    multipart
    0.24
    èĢĴ
    0.24
    iske
    0.24
    ANN
    0.23
    ders
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.