© 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. 4855
    Prev
    Next
    INDEX
    Explanations

    various followed by a noun

    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
    åįķåįķ
    -0.09
    éģ½
    -0.09
    æĸ°çļĦä¸Ģå¹´
    -0.09
    æīįåıijçİ°
    -0.09
    ç®į
    -0.08
    ä¸Ŀ毫
    -0.08
    æŁĦ
    -0.08
    /dom
    -0.08
    æ¯ıæ¯ı
    -0.08
    éĩįçĤ¹é¢ĨåŁŁ
    -0.08
    POSITIVE LOGITS
    åIJĦæł·
    0.15
    ä¸įåIJĮç¨ĭ度
    0.12
    åīįåı°
    0.10
    åIJĦ
    0.09
    大å°ı
    0.09
     çeÅŁitli
    0.09
     various
    0.09
    ushima
    0.09
    éĺ¶æ®µæĢ§
    0.09
     Highland
    0.09
    Activations Density 0.057%

    No Known Activations