© 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. 63350
    Prev
    Next
    INDEX
    Explanations

    signs, banners, chanting, burning

    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
    èĽĽ
    -0.09
    å¤ĸåĩº
    -0.09
    Č
    -0.09
    åľ¨å¤ĸ
    -0.09
    å¼Ģåı£
    -0.08
    æģĥ
    -0.08
    æľ¬èĥ½
    -0.08
    åĸĭ
    -0.08
     Fabric
    -0.08
    avern
    -0.08
    POSITIVE LOGITS
    èĩªåıij
    0.09
    绣ä¸Ģ
    0.09
     themselves
    0.09
    å¯ĵæĦı
    0.08
    æĸŃè£Ĥ
    0.08
    åĨĴçĿĢ
    0.08
    æīĺ
    0.08
    亲æīĭ
    0.08
    HM
    0.08
    ä¸ĢéĿ¢
    0.08
    Activations Density 0.195%

    No Known Activations