© 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. 8467
    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
    _confirmation
    -0.29
     manifest
    -0.27
     appeared
    -0.26
    ÑĪей
    -0.26
     appearances
    -0.26
     consciously
    -0.26
     six
    -0.26
     five
    -0.25
    æĮĤ
    -0.25
     appearance
    -0.24
    POSITIVE LOGITS
     Odds
    0.29
    ä¾Ľ
    0.27
    estone
    0.26
    uforia
    0.26
    ä¼ļä¸įä¼ļ
    0.26
    è¿ĺæĺ¯ä¼ļ
    0.26
    说ä¸įå®ļ
    0.26
     vö
    0.26
    centage
    0.25
    resco
    0.24
    Activations Density 0.129%

    No Known Activations

    This feature has no known activations.