© 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. 8081
    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
    欧ç¾İ
    -0.27
    èĢIJ
    -0.25
     Benn
    -0.25
    ä¹Łæ²¡æľī
    -0.24
    oline
    -0.24
     themselves
    -0.23
    [at
    -0.23
     rejo
    -0.23
    裸
    -0.23
     patent
    -0.23
    POSITIVE LOGITS
    ozo
    0.28
    FFE
    0.27
    Tra
    0.27
    èĥ±
    0.26
    羣缸
    0.26
    ä¸įä¸Ĭ
    0.24
     dedicated
    0.24
    æİĴ
    0.24
    æŃ£å®Ĺ
    0.24
    è±ĨèħIJ
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.