© 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. 7735
    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
    交æĺĵä¸Ńå¿ĥ
    -0.33
     captains
    -0.29
     fore
    -0.28
    idores
    -0.26
    ESPN
    -0.25
    çIJĨäºĭä¼ļ
    -0.25
    éĽı
    -0.24
     Äijứa
    -0.24
    alled
    -0.24
     fores
    -0.24
    POSITIVE LOGITS
    è¿ĻäºĽ
    0.28
    å¾Īæĥ³
    0.25
    .plot
    0.24
    ä¸įèī¯ä¿¡æģ¯
    0.24
     æı
    0.24
    éĢĻäºĽ
    0.24
     uncert
    0.23
    å»īä»·
    0.23
    æį¢äºĨ
    0.23
     StringComparison
    0.23
    Activations Density 0.087%

    No Known Activations

    This feature has no known activations.