© 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. 56984
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ç»Ļèĩªå·±
    -0.09
    çĤ¹å¤ļ
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    ãĤµãĥ©
    -0.09
    ä¹ĸ
    -0.09
    ochen
    -0.08
    åIJĦèĩª
    -0.08
    ear
    -0.08
    èŀŁ
    -0.08
    èĢģçĪ·åŃIJ
    -0.08
    POSITIVE LOGITS
    æĬĬæı¡
    0.09
     ÑıвлÑı
    0.09
    æĤ´
    0.08
    orsi
    0.08
     heavy
    0.08
     opin
    0.08
    moid
    0.08
    åı£è¢ĭ
    0.08
    LETE
    0.08
    eni
    0.08
    Activations Density 0.083%

    No Known Activations