© 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. 60855
    Prev
    Next
    INDEX
    Explanations

    progress and advances

    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
    æľīæĿ¡ä»¶
    -0.10
    强度
    -0.09
    rouch
    -0.09
    æݬ
    -0.09
    oller
    -0.08
    ughter
    -0.08
    è¿ĺæĥ³
    -0.08
    é¦Ĵ头
    -0.08
    èıģ
    -0.08
     tou
    -0.08
    POSITIVE LOGITS
     progress
    0.26
    è¿ĽæŃ¥
    0.26
    è¿Ľå±ķ
    0.23
    çļĦè¿ĽæŃ¥
    0.23
     Progress
    0.20
    progress
    0.20
    è¿Ľåº¦
    0.19
    	progress
    0.18
    Progress
    0.18
    -progress
    0.18
    Activations Density 0.066%

    No Known Activations