© 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. 26398
    Prev
    Next
    INDEX
    Explanations

    error messages or page issues

    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
    çĶľç¾İ
    -0.10
    èĢĥä¸Ĭ
    -0.09
    æĥij
    -0.08
     Caj
    -0.08
    ogne
    -0.08
    æł½
    -0.08
    åĪ»
    -0.08
     spare
    -0.08
    åŃĺæ´»
    -0.08
    æģª
    -0.08
    POSITIVE LOGITS
    临æŶ
    0.09
    é©»
    0.09
    é§IJ
    0.09
    æļĤæŶ
    0.09
    åıªå¥½
    0.08
    ocks
    0.08
    æķijæĬ¤
    0.08
    æij§
    0.08
    .Visibility
    0.08
    .IsValid
    0.08
    Activations Density 0.034%

    No Known Activations