© 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. 22842
    Prev
    Next
    INDEX
    Explanations

    my / her / our / their

    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
    çļĦ人æĿ¥è¯´
    -0.11
    åĵģçīĮçļĦ
    -0.10
     brink
    -0.09
    /from
    -0.09
    æ¯ıä¸Ģ个人
    -0.09
    åĽŀäºĭ
    -0.08
    æĪijåĸľæ¬¢
    -0.08
    人çļĦ
    -0.08
     midst
    -0.08
     pledge
    -0.08
    POSITIVE LOGITS
    缮çļĦæĺ¯
    0.15
     aim
    0.13
    æĦıæĢĿæĺ¯
    0.12
    ä¹ŁåĽłæѤ
    0.11
    çĿĢçľ¼
    0.11
     goal
    0.11
    éĩįå¿ĥ
    0.10
    ç¡®
    0.10
    æķ°æį®æĺ¾ç¤º
    0.10
    åīįæıIJæĺ¯
    0.10
    Activations Density 0.124%

    No Known Activations