© 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. 29419
    Prev
    Next
    INDEX
    Explanations

    good start

    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
    åħ¼
    -0.10
    æĺİå¹´
    -0.09
    ÑĨев
    -0.08
     paran
    -0.08
     currently
    -0.08
    eso
    -0.08
    currently
    -0.08
     нед
    -0.08
    .rb
    -0.08
    .setdefault
    -0.08
    POSITIVE LOGITS
    è§Ĥä¼Ĺ
    0.09
    ä¸ĭåįĬåľº
    0.09
    çļĦæĥħ绪
    0.09
    çļĦåIJĪä½ľ
    0.09
    åIJİç»Ń
    0.09
    迨
    0.09
    æħ¶
    0.09
    ä¸Ģæ³¢
    0.09
    åħ¨åľº
    0.09
    é»ĺå¥ij
    0.08
    Activations Density 0.040%

    No Known Activations