© 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. 60800
    Prev
    Next
    INDEX
    Explanations

    view frame

    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
    Ñĥни
    -0.09
    åĪĨåĮĸ
    -0.09
     enrich
    -0.09
    æ»´
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.08
    æķĻ导
    -0.08
    lessly
    -0.08
    uhan
    -0.08
    幡
    -0.08
    aron
    -0.08
    POSITIVE LOGITS
    ä¸Ģçľ¼
    0.13
    acular
    0.12
    eing
    0.11
    rale
    0.11
    .OnClickListener
    0.11
    ersh
    0.10
     Bale
    0.09
    pager
    0.09
    ç»ĵ
    0.09
    ðŁijĢ
    0.09
    Activations Density 0.126%

    No Known Activations