© 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. 22-TRANSCODER-HP
    7. 87804
    Prev
    Next
    INDEX
    Explanations

    Internet use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ĭåĬ¿
    -0.27
     ty
    -0.26
    zig
    -0.26
    ature
    -0.26
    ä¼ĺåĬ¿
    -0.25
    erv
    -0.24
    icap
    -0.24
    ospel
    -0.23
    atal
    -0.23
    vron
    -0.23
    POSITIVE LOGITS
     dissolution
    0.29
    è°ģéĥ½
    0.28
    æѤç§į
    0.28
     Drake
    0.26
    åĺ´å·´
    0.26
    éĢĤåIJĪèĩªå·±
    0.26
    åı³æīĭ
    0.25
    _accepted
    0.25
    aghan
    0.25
    æĸ°æµªè´¢ç»ı
    0.25
    Activations Density 0.003%

    No Known Activations