© 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. 51548
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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¸ĬæĿ¥
    -0.09
    çĨ¬
    -0.08
    istan
    -0.08
     Flame
    -0.08
    ansen
    -0.08
    åĴIJ
    -0.08
    ä¸įé«ĺ
    -0.08
    ror
    -0.08
    etes
    -0.07
    赶ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    rious
    0.10
    èĿĪ
    0.10
    æĶ¸
    0.10
    ä¸İåħ¶
    0.09
    åıĮçľ¼
    0.09
    æĸ°å¾ģç¨ĭ
    0.09
    =query
    0.09
     claws
    0.09
    宵
    0.09
    鹫
    0.08
    Activations Density 0.007%

    No Known Activations