© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26169
    Prev
    Next
    INDEX
    Explanations

    slang, caffeine

    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
    Negative Logits
    åIJįåįķ
    -0.09
    hood
    -0.09
    ä¸İæѤ
    -0.09
    SystemService
    -0.08
     اÙĦشر
    -0.08
     stron
    -0.08
    èĭĹ
    -0.08
    æķ´åIJĪ
    -0.08
    羣æŃ£çļĦ
    -0.08
    ancy
    -0.08
    POSITIVE LOGITS
    aken
    0.09
    rat
    0.09
    DOC
    0.09
    çļĦä¸ĢåĪĩ
    0.08
    ä½ľçī©
    0.08
    太æ¹ĸ
    0.08
     íļ
    0.08
    sdk
    0.08
    IER
    0.08
    rad
    0.08
    Activations Density 0.005%

    No Known Activations