© 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. 51369
    Prev
    Next
    INDEX
    Explanations

    English linguistic comparisons

    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
    ä»İåݻ年
    -0.10
    åīįéĿ¢
    -0.09
    ä¸ĭåįĬå¹´
    -0.09
    peater
    -0.09
    åĸĻ
    -0.09
    platform
    -0.09
    /platform
    -0.08
    _platform
    -0.08
    è·
    -0.08
     przeglÄħd
    -0.08
    POSITIVE LOGITS
     ours
    0.11
     today
    0.10
    æĪijä»¬ä¹Ł
    0.10
    ä»Ĭ天çļĦ
    0.10
    çݰ代
    0.09
    çݰ代社ä¼ļ
    0.09
    éĤ£ç§į
    0.09
     modern
    0.09
    æľ¬åľŁ
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    Activations Density 0.253%

    No Known Activations