© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    lists qualifiers and examples

    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
    logan
    -0.09
    äºĨåĩł
    -0.09
    æ³ķ人
    -0.09
    享åıĹ
    -0.09
    à¸Ķาว
    -0.09
    /gpl
    -0.08
    èĩªåĬ©
    -0.08
    icus
    -0.08
    åįĬå²Ľ
    -0.08
    plib
    -0.08
    POSITIVE LOGITS
    æĺ¯åIJ¦æľī
    0.15
    æĺ¯åIJ¦åŃĺåľ¨
    0.13
     whether
    0.12
    æĺ¯åIJ¦
    0.12
    æľī没æľī
    0.11
    è¦ģèĢĥèĻij
    0.11
     aspects
    0.11
    èĢĥèĻijåĪ°
    0.11
    æĸ¹éĿ¢
    0.10
     ìĸ¼ë§ĪëĤĺ
    0.10
    Activations Density 0.119%

    No Known Activations