© 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. 32853
    Prev
    Next
    INDEX
    Explanations

    seasons or years

    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
    åĨ·éĿĻ
    -0.10
    å¤įå·¥
    -0.09
    åįĬæľĪ
    -0.09
    éĺ²æ±Ľ
    -0.08
    æľ¬æľĪ
    -0.08
    交æį¢
    -0.08
    å½±
    -0.08
    天æ°Ķ
    -0.08
    é¢ĦåijĬ
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
    POSITIVE LOGITS
    æĶ¹éĿ©
    0.10
    éĢIJå¹´
    0.10
    åĬ±
    0.10
    åºķèķ´
    0.10
    å°¼æĸ¯
    0.09
    ENU
    0.09
     reform
    0.09
    屡
    0.09
    quo
    0.09
    æ¯ıå¹´
    0.09
    Activations Density 0.100%

    No Known Activations