© 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. 5174
    Prev
    Next
    INDEX
    Explanations

    Chey, Chy, Cheyene

    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
    ç¼Ķ
    -0.09
    unan
    -0.09
    åłĤ
    -0.09
    诤
    -0.09
    æĸĭ
    -0.08
     Lesser
    -0.08
    enheim
    -0.08
    é»Ŀ
    -0.08
    ÑıÑĤиÑı
    -0.08
    Å¡ÃŃ
    -0.08
    POSITIVE LOGITS
    èįĥ
    0.10
    adr
    0.10
    iel
    0.10
    å°ıå§IJ
    0.10
    æľĢæĸ°çļĦ
    0.10
    rie
    0.09
    èݪ
    0.09
    _utilities
    0.09
    失èIJ½
    0.09
    èħ¹éĥ¨
    0.09
    Activations Density 0.088%

    No Known Activations