© 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. 37400
    Prev
    Next
    INDEX
    Explanations

    US states/regions

    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
    鬼
    -0.09
    RSS
    -0.08
     RSS
    -0.08
    lia
    -0.07
    è®°å¿ĨåĬĽ
    -0.07
     kontakt
    -0.07
    ìłľ
    -0.07
    สะ
    -0.07
    èĤļ
    -0.07
    wap
    -0.07
    POSITIVE LOGITS
    没äºĭ
    0.10
    /commons
    0.10
    utex
    0.10
    èµ°åĩºæĿ¥
    0.10
    ä¸Ģæľµ
    0.09
    éĹ»
    0.09
    uve
    0.09
     ÑĢеÑĪи
    0.09
    ÃŃda
    0.09
    æľµ
    0.08
    Activations Density 0.144%

    No Known Activations