© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19945
    Prev
    Next
    INDEX
    Explanations

    your outcome, skin, Heart, status, spider

    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
    å¾Īå¥½åľ°
    -0.10
    ä¸įä½Ĩ
    -0.09
    没æľī太大
    -0.09
    å¾Ī强
    -0.09
    éĿŀ常éĢĤåIJĪ
    -0.09
    ä½ľä¸ºä¸Ģç§į
    -0.09
    å¾Ī好çļĦ
    -0.08
    è¾ĥ好çļĦ
    -0.08
    éĿŀ常好çļĦ
    -0.08
    è¾ĥå·®
    -0.08
    POSITIVE LOGITS
    çĦ±
    0.09
    à¹ģห
    0.08
    åħ¥
    0.08
    uces
    0.08
    åIJĽ
    0.08
     ÐĴедÑĮ
    0.08
    æĵį
    0.08
    åĩ»
    0.08
     صØŃ
    0.08
    æ°¸ä¸į
    0.07
    Activations Density 0.022%

    No Known Activations