© 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. 56423
    Prev
    Next
    INDEX
    Explanations

    now / currently

    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
    æ°¸æģĴ
    -0.11
    owie
    -0.10
    ç¾ģ
    -0.09
    ç»İ
    -0.09
    æīĵå¾Ĺ
    -0.09
    adays
    -0.09
    izzle
    -0.09
    å°½
    -0.09
    ä¸¤å¼ł
    -0.09
    åķ¬
    -0.09
    POSITIVE LOGITS
     now
    0.36
    çİ°åľ¨
    0.31
    now
    0.29
     ÑĤепеÑĢÑĮ
    0.28
    å¦Ĥä»Ĭ
    0.25
     ahora
    0.24
     Now
    0.23
    	now
    0.23
    Now
    0.23
    _now
    0.22
    Activations Density 0.381%

    No Known Activations