© 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. 32-TRANSCODER-HP
    7. 42089
    Prev
    Next
    INDEX
    Explanations

    say "g" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ±ī
    -0.29
    æ±Ĺ
    -0.29
    yü
    -0.29
    porn
    -0.29
    EUR
    -0.28
    æ¼¢
    -0.28
     Äijá»ĵ
    -0.28
    ALLE
    -0.28
    andle
    -0.28
     kenn
    -0.27
    POSITIVE LOGITS
    rg
    0.33
    letic
    0.28
    èĩªæľī
    0.28
    论
    0.27
    .isTrue
    0.27
    就没æľī
    0.26
    acious
    0.26
    æĹ¥äº§
    0.26
    éĤ£ä½į
    0.25
    产
    0.25
    Activations Density 0.003%

    No Known Activations