© 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. 59290
    Prev
    Next
    INDEX
    Explanations

    nutritional components

    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
    循
    -0.09
    åģĩæĹ¥
    -0.09
    åħ¥åºĵ
    -0.09
    gio
    -0.09
     Bale
    -0.08
    çļĦæĶ¯æĮģ
    -0.08
    åģĩæľŁ
    -0.08
    amba
    -0.08
    ä¸įæħİ
    -0.08
    Ñģп
    -0.08
    POSITIVE LOGITS
    åĮ£
    0.10
    åıĮæīĭ
    0.09
    æłİ
    0.09
    åĴ½
    0.09
    åŬ
    0.09
    棱
    0.09
    /fs
    0.08
    亲æīĭ
    0.08
    第ä¸Ģ家
    0.08
    æīĭå·¥
    0.08
    Activations Density 0.057%

    No Known Activations