© 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. 58523
    Prev
    Next
    INDEX
    Explanations

    not know

    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
    ONGO
    -0.11
    çĮ¿
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.10
    æŃ£åľ¨è¿Ľè¡Į
    -0.10
    APON
    -0.09
    OWER
    -0.09
    NAV
    -0.09
    åľ¨ä¹İ
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.08
    utow
    -0.08
    POSITIVE LOGITS
    ä¸įæĥľ
    0.09
    åĬ¨éĿĻ
    0.08
    æĿľç»Ŀ
    0.08
    Mos
    0.08
    æł¸å¿ĥæĬĢæľ¯
    0.08
    éĿ¢çĽ®
    0.08
     trick
    0.08
     concrete
    0.08
    解åĨ³äºĨ
    0.08
     Churches
    0.08
    Activations Density 0.050%

    No Known Activations