© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20997
    Prev
    Next
    INDEX
    Explanations

    ask and answer questions

    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
    æĪª
    -0.10
    çĸ½
    -0.09
    è·Łä½ł
    -0.09
    éĿ
    -0.08
    o
    -0.08
    éĤ£æ¬¡
    -0.08
    æĪijä¸įçŁ¥éģĵ
    -0.08
    -shadow
    -0.08
    -ray
    -0.08
    hammer
    -0.08
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.15
    æľ¬èº«
    0.12
    ç»ĻåĪ«äºº
    0.11
    æľ¬èº«çļĦ
    0.11
     lẫn
    0.11
    ä¸Ģæĸ¹
    0.10
    åĪ«äººçļĦ
    0.10
    ä»ĸ人
    0.10
    æĶ¹éĢł
    0.10
    à¹Ģà¸Ńà¸ĩ
    0.10
    Activations Density 0.170%

    No Known Activations