© 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. 34234
    Prev
    Next
    INDEX
    Explanations

    installable rules, news URLs, charts, APPLE products, wish list

    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
     êµī
    -0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.10
    [âĢ¦
    -0.09
    ANGO
    -0.09
    羣æĺ¯å¤ª
    -0.09
     ìĬ¤ìĬ¤
    -0.09
    ãģªãģĭãģªãģĭ
    -0.09
    ê¼´
    -0.09
    âķŃ
    -0.09
    UTH
    -0.09
    POSITIVE LOGITS
    \/
    0.09
    å¼Ħ
    0.06
    åħĦå¼Ł
    0.06
    ane
    0.06
     \/
    0.06
    athon
    0.06
    PA
    0.06
    æĻ¨æĬ¥
    0.06
    æľ¬è½®
    0.06
    æĹłæīĢè°ĵ
    0.06
    Activations Density 1.143%

    No Known Activations