© 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. 60742
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
    èݼ
    -0.09
    æľŁåĨħ
    -0.09
    ä¹Łæĺ¯
    -0.09
    ÂĢÂĻ
    -0.08
    çĿ
    -0.08
    çŀħ
    -0.08
    ayah
    -0.08
    (Arg
    -0.08
     ли
    -0.08
    èļ©
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.12
     пÑĢоÑģ
    0.10
    çĶļèĩ³
    0.10
    åħ¥æĪ·
    0.09
    åįķ纯çļĦ
    0.09
     кÑĥд
    0.09
    çŁ¥æĥħ
    0.09
    oj
    0.09
    æ¯ĵ
    0.09
    æĴ¬
    0.08
    Activations Density 0.251%

    No Known Activations