© 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. 47766
    Prev
    Next
    INDEX
    Explanations

    philanthropy

    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
    -up
    -0.08
    æĴ
    -0.08
    æ²£
    -0.08
    æ°ijå¿ĥ
    -0.08
    inator
    -0.08
    åıįèħIJåĢ¡å»ī
    -0.08
    falls
    -0.08
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.08
    æIJĶ
    -0.07
    ãģ¾ãģ£ãģŁ
    -0.07
    POSITIVE LOGITS
    opsis
    0.10
    çĶļä¹Ī
    0.10
    满满
    0.09
    sic
    0.09
    DBG
    0.09
    ancy
    0.09
    åķ¬
    0.09
     вÑĢем
    0.09
    kart
    0.09
    sı
    0.09
    Activations Density 0.006%

    No Known Activations