© 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. 8815
    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
    夥
    -0.28
     pron
    -0.28
    ue
    -0.26
    endir
    -0.26
    least
    -0.25
    launch
    -0.25
    ended
    -0.24
    Least
    -0.24
    ÑĪки
    -0.24
    cmp
    -0.24
    POSITIVE LOGITS
    æĥħæĦŁ
    0.25
    çļĦæĹ¶ä»£
    0.25
    ilight
    0.24
    ä¹ĭæĦı
    0.24
    Yesterday
    0.24
    伯
    0.23
    idia
    0.23
    è¡°èĢģ
    0.23
    åħ¨åľº
    0.23
    zano
    0.23
    Activations Density 0.046%

    No Known Activations

    This feature has no known activations.