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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6117
    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
     tem
    -0.29
     tempo
    -0.27
    eni
    -0.27
    éĿ¢æĿ¿
    -0.26
    帮ä»ĸ
    -0.26
    anus
    -0.26
    OPY
    -0.25
     panel
    -0.25
     covert
    -0.25
     presumably
    -0.24
    POSITIVE LOGITS
    subclass
    0.31
    è¯ł
    0.29
    æĢ»ä½ĵè§ĦåĪĴ
    0.28
    SCALE
    0.26
    ÑĥÑģÑĤ
    0.26
     zag
    0.26
    ç©°
    0.25
    "},"
    0.25
    à¸Ľà¸ģà¸Ħรà¸Ńà¸ĩ
    0.25
    å¿«é¤IJ
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.