© 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. 49571
    Prev
    Next
    INDEX
    Explanations

    speaking or put simply

    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
    åı®
    -0.11
    æłİ
    -0.10
    çľĭä¸įè§ģ
    -0.10
    æĹħ
    -0.10
    髯
    -0.10
    ansk
    -0.09
    åģļçļĦäºĭ
    -0.09
    ç»IJ
    -0.09
    åŀĦæĸŃ
    -0.09
    ä¸¥æł¼æĮīçħ§
    -0.09
    POSITIVE LOGITS
     Twe
    0.08
    irs
    0.08
    etical
    0.08
    榻
    0.08
    zioni
    0.08
    zial
    0.08
    ajs
    0.08
    ormal
    0.08
     Hank
    0.08
    æĸĩåĮĸåºķèķ´
    0.08
    Activations Density 0.010%

    No Known Activations