© 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. 47585
    Prev
    Next
    INDEX
    Explanations

    code examples with arrays

    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
    饬
    -0.09
    åı¯è§Ĥ
    -0.09
    nost
    -0.08
    ily
    -0.08
    empt
    -0.08
     scalp
    -0.08
    aries
    -0.08
    0
    -0.08
     princ
    -0.08
    ç»ıéªĮåĴĮ
    -0.08
    POSITIVE LOGITS
    (Expected
    0.09
    åħ¬çĶ¨
    0.09
    ãģ¨ãģĦãģ£ãģŁ
    0.08
    æĪijåĸľæ¬¢
    0.08
     antiqu
    0.08
    /Peak
    0.08
    ç±į
    0.08
    .ElementAt
    0.08
    /or
    0.08
    antes
    0.08
    Activations Density 0.716%

    No Known Activations