© 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. 36845
    Prev
    Next
    INDEX
    Explanations

    caused a stir / storm

    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
    ç»ıåİĨ
    -0.09
    çµ®
    -0.09
     Wool
    -0.08
    严åİīæīĵåĩ»
    -0.08
    éĤĪ
    -0.08
    æĸ¥
    -0.08
    åįĴ
    -0.08
     grop
    -0.08
    çĽĪåĪ©èĥ½åĬĽ
    -0.08
     ÑģкоÑĢ
    -0.08
    POSITIVE LOGITS
    ä¸Ģéĺµ
    0.11
    ä¸įå°ıçļĦ
    0.11
    ç¯ĵ
    0.11
    é²
    0.10
    éªļ
    0.10
    ä½ľèĢħæľ¬äºº
    0.09
    æķĪåºĶ
    0.09
    cpy
    0.09
    æ³¥åľŁ
    0.09
    æ··ä¹±
    0.09
    Activations Density 0.039%

    No Known Activations