© 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. 64010
    Prev
    Next
    INDEX
    Explanations

    uptake, uptown, uptrend, uptime, UPTOWN

    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
    åģľä¸ĭæĿ¥
    -0.10
    妤
    -0.09
    rz
    -0.09
    è¯ļ
    -0.09
    ì±ħ
    -0.08
    iele
    -0.08
     Jeh
    -0.08
    æĺİç¡®
    -0.08
    zelf
    -0.08
    æµ´
    -0.08
    POSITIVE LOGITS
    /down
    0.10
    ILON
    0.10
    ancy
    0.09
    åģļæ³ķ
    0.09
    eous
    0.09
    人家
    0.09
    ä¹ĭä½ľ
    0.09
    ucky
    0.09
    ł
    0.09
    /out
    0.09
    Activations Density 0.017%

    No Known Activations