© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4772
    Prev
    Next
    INDEX
    Explanations

    .com links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¥èĩª
    -0.10
    adoo
    -0.09
    erie
    -0.08
    stä
    -0.08
    ines
    -0.08
     Ãľrün
    -0.08
    ä¾ĽåºĶåķĨ
    -0.08
    溪
    -0.08
    .Bundle
    -0.08
    ró
    -0.08
    POSITIVE LOGITS
    .org
    0.12
    ä¸ĬçļĦ
    0.11
    ä¸Ĭæľī
    0.10
    isible
    0.10
    èĿ®
    0.09
    åį¤
    0.09
    åŃIJå¼Ł
    0.09
    æªĢ
    0.09
    ç«Ļ
    0.09
    trys
    0.09
    Activations Density 0.213%

    No Known Activations