© 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. 58402
    Prev
    Next
    INDEX
    Explanations

    may or might followed by a verb

    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
    èĨ¨
    -0.10
    ä¿¡ç®±
    -0.10
    aint
    -0.09
    æĹ¥æ¸IJ
    -0.09
    æľīåħ³éĥ¨éŨ
    -0.09
    ç§ģèĩª
    -0.08
    æłĹ
    -0.08
    人æīį
    -0.08
    éĿĻéĿĻ
    -0.08
    mr
    -0.08
    POSITIVE LOGITS
    -times
    0.12
    èķ¨
    0.11
     ÙĬÙĥÙĪÙĨ
    0.10
    è§īå¾Ĺ
    0.10
    ä¼ļåıijçĶŁ
    0.09
    ä¹Łåı¯èĥ½
    0.09
    ä¼ļéķ¿
    0.09
    ä¸įä¸Ģå®ļ
    0.09
     تÙĥÙĪÙĨ
    0.09
    éģį
    0.09
    Activations Density 0.216%

    No Known Activations