© 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. 36423
    Prev
    Next
    INDEX
    Explanations

    reports on

    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
    ulta
    -0.09
    ä¸įç¦ģ
    -0.08
    eters
    -0.08
     вне
    -0.08
    inho
    -0.08
    çļĦèĢģ
    -0.08
    overs
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    æĬĢæľ¯åĴĮ
    -0.08
     Pierce
    -0.08
    POSITIVE LOGITS
    æ³Į
    0.11
    俯
    0.10
    รà¸ĵ
    0.09
    ç¹ĩ
    0.09
    å¾ĩ
    0.09
    itor
    0.09
    æĮĽ
    0.09
    _activate
    0.08
    类产åĵģ
    0.08
    涧
    0.08
    Activations Density 0.121%

    No Known Activations