© 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. 8674
    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
    æĸ¹å¼ıè¿Ľè¡Į
    -0.27
    èĿ¶
    -0.25
     slog
    -0.25
     vos
    -0.25
    emy
    -0.25
     Boyd
    -0.25
    壽
    -0.24
    edImage
    -0.24
    æľºåĬ¨
    -0.24
    cec
    -0.24
    POSITIVE LOGITS
    -mf
    0.27
     Marketplace
    0.27
     canopy
    0.25
    rink
    0.25
    idle
    0.24
    åħ¸èĮĥ
    0.24
    åIJijä¸Ĭ
    0.24
    auto
    0.24
    åļ¼
    0.23
    好似
    0.23
    Activations Density 0.167%

    No Known Activations

    This feature has no known activations.