© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22261
    Prev
    Next
    INDEX
    Explanations

    founded in or 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
    IfExists
    -0.09
    åŀŃ
    -0.09
    severity
    -0.09
    éĩįå·¥
    -0.08
    å¢ŀåĢ¼æľįåĬ¡
    -0.08
    èħ¹
    -0.08
     اÙĦÙħÙĨت
    -0.08
    \Contracts
    -0.08
    _CC
    -0.08
    延éķ¿
    -0.08
    POSITIVE LOGITS
    æĪIJç«ĭ
    0.13
    æĪIJç«ĭäºĨ
    0.13
    å®ĹæŨ
    0.11
    æĪIJç«ĭäºİ
    0.10
    åĪĿè¡·
    0.10
     founded
    0.09
    æ²Ł
    0.09
    溪
    0.09
    åı®
    0.09
    ç®ĹäºĨ
    0.09
    Activations Density 0.081%

    No Known Activations