© 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. 10319
    Prev
    Next
    INDEX
    Explanations

    high-level

    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
    èİł
    -0.10
    æĸ¹éĿ¢çļĦ
    -0.09
    妨
    -0.09
    æ³¢çī¹
    -0.09
    ä½İä¸ĭ
    -0.09
    é¢ī
    -0.09
    åĿİåĿ·
    -0.09
    åįĹå±±
    -0.09
    尤为
    -0.09
    èµĤ
    -0.09
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.08
    -found
    0.08
     DOI
    0.08
    оказ
    0.08
    allel
    0.08
    ossip
    0.07
    é¢Ĩä¼ļ
    0.07
     示
    0.07
     shorten
    0.07
    kre
    0.07
    Activations Density 0.024%

    No Known Activations