© 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. 36824
    Prev
    Next
    INDEX
    Explanations

    time spent

    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
    åĺ´è§Ĵ
    -0.10
    ä¸Ńè¶ħ
    -0.10
    æ°ĶåĢĻ
    -0.09
    ç´¯
    -0.09
    侧éĿ¢
    -0.09
    psy
    -0.09
    CCI
    -0.08
    å¿ĥåºķ
    -0.08
    ieres
    -0.08
    è¿ĩé«ĺ
    -0.08
    POSITIVE LOGITS
    çļĦæľºä¼ļ
    0.12
     time
    0.11
    é¢ł
    0.11
    ван
    0.10
    time
    0.10
    æŶéĹ´
    0.10
    æŶåħī
    0.10
    çļĦæŶéĹ´
    0.09
    æŶéĹ´ä¸º
    0.09
     rest
    0.09
    Activations Density 0.043%

    No Known Activations