© 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. 58641
    Prev
    Next
    INDEX
    Explanations

    "topic" or "subject"

    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
    ürn
    -0.09
    è´¢ç»ı
    -0.09
    emoji
    -0.09
    è¯ł
    -0.09
    äºĨåIJĹ
    -0.08
    ä½ľæģ¯
    -0.08
    对ä»ĸ
    -0.08
    illi
    -0.08
    æĺ±
    -0.08
    ç³ĸ
    -0.08
    POSITIVE LOGITS
    æĥħåĨµ
    0.16
     situation
    0.14
    åľºåIJĪ
    0.13
    æĥħå½¢
    0.13
    äºĭåĦ¿
    0.12
    åĽŀäºĭ
    0.12
    äºĭæĥħ
    0.12
    æĥħæ³ģ
    0.12
    åŀĤ
    0.12
    æĥħåĨµè¿Ľè¡Į
    0.11
    Activations Density 0.187%

    No Known Activations