© 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. 8302
    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
    ibur
    -0.33
    æıIJ
    -0.26
    èĢĮåIJİ
    -0.25
    mast
    -0.25
    æĪŁ
    -0.25
     Crime
    -0.24
    æİĸ
    -0.24
    çģ°èī²
    -0.24
    æįī
    -0.24
    Wins
    -0.24
    POSITIVE LOGITS
    å°±æĺ¯
    0.25
    agedList
    0.25
    é¦Ļ
    0.25
    ä»ĬæĻļ
    0.24
    è´¡çĮ®
    0.24
    additional
    0.24
    æĹ©æĻļ
    0.24
    well
    0.23
    èĩªæľī
    0.23
    èĬĿ
    0.23
    Activations Density 1.155%

    No Known Activations

    This feature has no known activations.