© 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. 8062
    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
    磬
    -0.26
     comb
    -0.25
    inc
    -0.24
    rstrip
    -0.24
     certain
    -0.24
    éģ£
    -0.23
    -
    -0.23
    ä¸Ģå®ļ
    -0.23
     пÑĢедмеÑĤ
    -0.23
    ismic
    -0.23
    POSITIVE LOGITS
    æľī人
    0.28
    è¿ĩç¨ĭ
    0.27
    ä¸įä¸ĭ
    0.27
     Bowen
    0.26
    éĢĨè¡Į
    0.25
    æĹłéļľç¢į
    0.24
    zte
    0.24
    èººåľ¨
    0.24
    éĤ£æ®µ
    0.24
     trending
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.