© 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. 56404
    Prev
    Next
    INDEX
    Explanations

    well equipped

    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
    æѤåĪ»
    -0.10
    ä½łçİ°åľ¨
    -0.10
    è¿Ļä¸ĢåĪ»
    -0.10
    çģ«çĥŃ
    -0.10
    ç³Ĺ
    -0.09
    Ñıн
    -0.09
    æ²¥
    -0.09
    ä»ĸå·²ç»ı
    -0.09
    æ¸İ
    -0.08
    æİ·
    -0.08
    POSITIVE LOGITS
     оÑĤзÑĭв
    0.09
    èĪįå¾Ĺ
    0.09
    æľįåĬ¡è´¨éĩı
    0.09
    åĤįæĻļ
    0.08
    моÑĢ
    0.08
    æĢ»ä½ĵ
    0.08
    ----------------------------------------------------------------------
    0.08
    à§İ
    0.08
    溯
    0.08
     staffing
    0.08
    Activations Density 0.066%

    No Known Activations