© 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. 8547
    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
    gee
    -0.30
    æ¿Ģ
    -0.28
     Countdown
    -0.26
    è¯Ńè¨Ģ
    -0.25
    _party
    -0.25
    qli
    -0.25
    ework
    -0.24
    iston
    -0.24
    plode
    -0.24
    åĬ¨ä½ľ
    -0.24
    POSITIVE LOGITS
    äºĮåįģåĽĽ
    0.26
    **
    0.26
    èĭ±æĸĩ
    0.25
    osite
    0.25
    ä¹°ä¸ľè¥¿
    0.24
    æįº
    0.24
    —
    0.23
     samen
    0.23
    inqu
    0.23
     carries
    0.23
    Activations Density 0.684%

    No Known Activations

    This feature has no known activations.