© 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. 9099
    Prev
    Next
    INDEX
    Explanations

    times with colon

    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¯ı次éĥ½
    -0.09
    å©ļåIJİ
    -0.08
    æīĴ
    -0.08
    èĩ»
    -0.08
    	TokenName
    -0.08
    ULER
    -0.08
    循
    -0.08
    è¿Ļ件
    -0.08
    ç¹ĩ
    -0.08
    件
    -0.08
    POSITIVE LOGITS
    æŶéĹ´æ®µ
    0.09
     Shapiro
    0.09
     intervals
    0.09
     interval
    0.09
    æĹ¶æ®µ
    0.09
     prol
    0.09
    æĬµè¾¾
    0.08
    涧
    0.08
    ä»¥äººä¸ºæľ¬
    0.08
    oden
    0.08
    Activations Density 0.046%

    No Known Activations