© 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. 823
    Prev
    Next
    INDEX
    Explanations

    public image and credibility

    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
    è´¯éĢļ
    -0.10
    æĶĢ
    -0.10
    åī¥å¤º
    -0.09
    åĬĽæ±Ĥ
    -0.09
    èµĦè´¨
    -0.09
    ä¸įåģľåľ°
    -0.09
    读æĩĤ
    -0.09
    SAFE
    -0.09
    äºĨ解ä¸Ģä¸ĭ
    -0.09
    çŃ¹éĽĨ
    -0.09
    POSITIVE LOGITS
    è¿Ļ座
    0.09
     наÑĢ
    0.08
    æĨĶ
    0.08
    åĨįä¹Łä¸į
    0.08
    ugin
    0.08
    assin
    0.08
    avana
    0.08
     thất
    0.08
    èªĬ
    0.08
     Jamal
    0.08
    Activations Density 0.037%

    No Known Activations