© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57525
    Prev
    Next
    INDEX
    Explanations

    duality, past, personality, circumstances, construct, toxicological

    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
    ToFile
    -0.09
     Buch
    -0.09
    循
    -0.09
    æĿ¥å½¢å®¹
    -0.09
     Raymond
    -0.08
    è°£
    -0.08
    åijĬ
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    示æĦı
    -0.08
    æĩĴ
    -0.08
    POSITIVE LOGITS
    åŁ·
    0.10
    å¢ĥ
    0.10
    æĢ¥äºİ
    0.10
    æĪij们认为
    0.09
    æī§çĿĢ
    0.09
    åĹĶ
    0.09
    é¢ł
    0.09
    è¿Ľåĩºåı£
    0.09
    ihar
    0.09
    侯
    0.08
    Activations Density 0.070%

    No Known Activations