© 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. 58302
    Prev
    Next
    INDEX
    Explanations

    seasonal months, holidays, summer, May

    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
    åIJĪçIJĨçļĦ
    -0.11
    ä¸ĢæĹ¥
    -0.10
    stances
    -0.10
     promoters
    -0.10
    çļĦä¸ĢéĿ¢
    -0.10
    oples
    -0.10
    stadt
    -0.10
    æĺĿ
    -0.09
    å½ĵæĹ¥
    -0.09
    é¢ı
    -0.09
    POSITIVE LOGITS
    äºļ马éĢĬ
    0.09
    æ¯Ļ
    0.08
    åĨĻåĩº
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    æĥ¯
    0.08
    åŃ£èĬĤ
    0.08
     TODO
    0.08
    utilus
    0.08
    æİ·
    0.08
     dead
    0.07
    Activations Density 0.093%

    No Known Activations