© 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. 51749
    Prev
    Next
    INDEX
    Explanations

    over time

    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
    产åĢ¼
    -0.09
    ä»įåľ¨
    -0.09
    ä¸įç®¡ä½ł
    -0.09
     Gow
    -0.08
    Monad
    -0.08
    åĪİ
    -0.08
    _tools
    -0.08
    ä¸ĢçĽ´åľ¨
    -0.08
    åĪ°å¤Ħ
    -0.08
    åĤĻ
    -0.08
    POSITIVE LOGITS
    ä¹ħäºĨ
    0.25
    éļıçĿĢæŶéĹ´
    0.21
    ä¸Ģ段æŶéĹ´
    0.20
    éĢIJæ¸IJ
    0.16
    æ¸IJæ¸IJ
    0.15
    ä¹ħ
    0.15
     dần
    0.14
    æħ¢æħ¢åľ°
    0.14
    æħ¢æħ¢çļĦ
    0.13
    ä¸įä¹ħ
    0.13
    Activations Density 0.047%

    No Known Activations