© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4811
    Prev
    Next
    INDEX
    Explanations

    Crime, military, and politics

    np_max-act · gemini-2.0-flash
    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
    ep
    -0.27
     reaction
    -0.26
    èĻ¹æ¡¥
    -0.26
    ORM
    -0.25
    éĢļ
    -0.24
     UsersController
    -0.24
     West
    -0.24
    _preference
    -0.24
    ush
    -0.24
    adio
    -0.23
    POSITIVE LOGITS
    auty
    0.28
    autiful
    0.27
     fres
    0.26
    åIJĦæł·
    0.26
    venir
    0.26
    ctors
    0.25
    allis
    0.25
     fresh
    0.25
    æĹłæĦı
    0.25
     kindly
    0.24
    Activations Density 0.011%

    No Known Activations