© 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. 3812
    Prev
    Next
    INDEX
    Explanations

    sorted by / ranked by

    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
    åħ±åIJĮä½ĵ
    -0.12
    åĢ¡å¯¼
    -0.11
     Sachs
    -0.10
    æıIJåĢ¡
    -0.10
    rium
    -0.10
    æ¢Ĩ
    -0.09
    OSH
    -0.09
    笾
    -0.09
    ä¼Ĭæĭī
    -0.09
    对æłĩ
    -0.09
    POSITIVE LOGITS
    è´¨éĩıåĴĮ
    0.10
     how
    0.09
     age
    0.09
    yal
    0.09
     Stuart
    0.08
    ç»ıéªĮåĴĮ
    0.08
    梦æĥ³
    0.08
    åħ¶æīĢ
    0.08
    lef
    0.08
    éļ¶å±ŀ
    0.08
    Activations Density 0.082%

    No Known Activations