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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9031
    Prev
    Next
    INDEX
    Explanations

    Clifford delivered

    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
    ipp
    -0.09
    Ñĥл
    -0.09
    æ³°å±±
    -0.09
    æķĪ
    -0.09
    æ½ľ
    -0.09
    oret
    -0.08
    inate
    -0.08
    inous
    -0.08
    碣
    -0.08
    æĥħæĻ¯
    -0.08
    POSITIVE LOGITS
    èĭ·
    0.10
    å®°
    0.09
    æ´Ĺè¡£
    0.09
    ç²½åŃIJ
    0.09
    ä¸Ģä¸Ŀ
    0.09
    ssi
    0.09
    å®ĺåı¸
    0.09
    ä»ĸèĩªå·±
    0.08
    ç«Ļèµ·æĿ¥
    0.08
    çļĦæł·åŃIJ
    0.08
    Activations Density 0.002%

    No Known Activations