© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 718
    Prev
    Next
    INDEX
    Explanations

    cooking time

    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
    Negative Logits
    èݲèĬ±
    -0.09
    ç¼ĵ解
    -0.09
    -pill
    -0.09
    èĤļ
    -0.09
    pective
    -0.08
    ä¸įå®Į
    -0.08
    æıIJæ¡Ī
    -0.08
    æĮ¨
    -0.08
    odable
    -0.08
    igure
    -0.08
    POSITIVE LOGITS
    æĻ¨æĬ¥
    0.10
    åĢĴåħ¥
    0.10
    _processes
    0.10
    èĢIJå¿ĥ
    0.10
    è¿ĩç¨ĭ
    0.09
    æĵįä½ľ
    0.09
    çļĦæĵįä½ľ
    0.09
     process
    0.09
    çĬ¯
    0.09
    gon
    0.09
    Activations Density 0.227%

    No Known Activations