© 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. 16812
    Prev
    Next
    INDEX
    Explanations

    look up

    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
    ãģľ
    -0.09
    irt
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
    èĤīä½ĵ
    -0.08
    lez
    -0.08
    æĹłå£°
    -0.08
    ä¸ĸä¿Ĺ
    -0.08
    irut
    -0.08
    æ°¸ä¸į
    -0.08
    åħ®
    -0.08
    POSITIVE LOGITS
    OrCreate
    0.11
    å¹Į
    0.09
    ä¸Ģ举
    0.09
    æ¸ħæ¥ļ
    0.08
    åĽ½æĥħ
    0.08
    asz
    0.08
    æ¿ĢåĬ¨
    0.08
    ffi
    0.08
    ä»Ģä¹Īæĺ¯
    0.08
    åĩºæĿ¥
    0.08
    Activations Density 0.015%

    No Known Activations