© 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. 47668
    Prev
    Next
    INDEX
    Explanations

    follow-up timelines

    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
    ilk
    -0.09
    楼æĪ¿
    -0.08
    ä¹ĭ家
    -0.08
    alse
    -0.08
    è¡Įãģį
    -0.08
     اÙĦÙħÙĩ
    -0.08
    å¤ĩ
    -0.08
    ric
    -0.08
    åħ´èĩ´
    -0.08
     Ach
    -0.08
    POSITIVE LOGITS
     follow
    0.10
    è·Łè¿Ľ
    0.10
    æľŁ
    0.10
    è·Łè¸ª
    0.09
    æľĢéķ¿
    0.09
    è·Łéļı
    0.09
    ä¸ī个æľĪ
    0.08
    è·ŁçĿĢ
    0.08
    追踪
    0.08
    éĩĮç¨ĭç¢ij
    0.08
    Activations Density 0.504%

    No Known Activations