© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7603
    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
    ä¸Ńè¶ħ
    -0.27
    å·²ç»ıå¼Ģå§ĭ
    -0.25
    èĦ¸
    -0.25
    æĹ¥æ¶Īæģ¯
    -0.25
    ân
    -0.25
     canyon
    -0.25
    èĢĻ
    -0.25
    han
    -0.24
    æĭ¼
    -0.24
     Ras
    -0.24
    POSITIVE LOGITS
    tres
    0.26
    kp
    0.26
    å¯Įæľī
    0.26
    interrupt
    0.26
    oven
    0.24
    pawn
    0.24
    è¿Ļéĥ¨åĪĨ
    0.24
    ORDER
    0.24
     imagePath
    0.23
    _Order
    0.23
    Activations Density 0.083%

    No Known Activations

    This feature has no known activations.