© 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. 9005
    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
    now
    -0.29
    ä»ĵä½į
    -0.26
    ’es
    -0.26
     Went
    -0.25
    uhan
    -0.25
     now
    -0.24
    _wallet
    -0.24
    ä¸ĬæĿ¥
    -0.24
    常
    -0.23
    Now
    -0.23
    POSITIVE LOGITS
     councils
    0.25
    axy
    0.25
    EDI
    0.24
    åĴ¨
    0.24
     reshape
    0.24
    å¢ĥ
    0.24
    EIF
    0.24
    ueling
    0.24
    URE
    0.23
    å°ı女åŃ©
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.