© 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. 19168
    Prev
    Next
    INDEX
    Explanations

    meaning of 'deterministic'" , "means real growth" , "means less capital" , "means spending the whole day"

    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
    æŃ£å½ĵ
    -0.09
    æķ£å¸ĥ
    -0.09
    ä»»ä½ķä¸Ģ个
    -0.09
    ancock
    -0.09
    ç»ĻäºĪäºĨ
    -0.09
    åı¯æݧ
    -0.09
    èµĮåľº
    -0.09
    åĵªæĢķ
    -0.09
    æĹłæĦı
    -0.08
    ertainment
    -0.08
    POSITIVE LOGITS
    è¦ģæľī
    0.10
    ä¸įä»ħè¦ģ
    0.10
     Ñģобой
    0.09
    å°±è¦ģ
    0.09
    peat
    0.08
    çļĦå°±æĺ¯
    0.08
    å¥Ķèµ´
    0.08
    离ä¸įå¼Ģ
    0.08
    笼
    0.08
    æĹ¢è¦ģ
    0.08
    Activations Density 0.031%

    No Known Activations