© 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. 50096
    Prev
    Next
    INDEX
    Explanations

    chair and seating adjustments

    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
    å±IJ
    -0.09
    室å¤ĸ
    -0.09
    плав
    -0.09
    涸
    -0.08
    æĹ¶è¡¨ç¤º
    -0.08
    èħĮ
    -0.08
    æĴ¼
    -0.08
    лав
    -0.08
    åĪ¶åīĤ
    -0.08
    åħįç¨İ
    -0.08
    POSITIVE LOGITS
    åĿIJçĿĢ
    0.15
    座ä½į
    0.15
    åĿIJ
    0.15
    æ¤ħåŃIJ
    0.14
    座æ¤ħ
    0.14
    æ¤ħ
    0.14
    å±ģèĤ¡
    0.11
    ç«Ļèµ·æĿ¥
    0.11
    躺
    0.11
     chairs
    0.11
    Activations Density 0.133%

    No Known Activations