© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    chain email

    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
    iku
    -0.10
    æĹ¥å¤ľ
    -0.09
    çĭ¬ç«ĭ
    -0.09
    仪表
    -0.09
     Lone
    -0.08
    并ä¸İ
    -0.08
    FREE
    -0.08
    orm
    -0.08
    æľºåĬ¨
    -0.08
    æļ´åĬĽ
    -0.08
    POSITIVE LOGITS
    æİ¥åĬĽ
    0.17
    éĵ¾æĿ¡
    0.14
    ä¼łéĢĴ
    0.13
    çĽ¸ä¼ł
    0.12
    ä¼łçIJĥ
    0.12
    éĵ¾
    0.11
    å±Ĥå±Ĥ
    0.11
    ä¼łæĴŃ
    0.11
     chain
    0.11
     коллекÑĤив
    0.11
    Activations Density 0.102%

    No Known Activations