© 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. 35403
    Prev
    Next
    INDEX
    Explanations

    `.com` or `://` followed by path

    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
    éĹª
    -0.09
    ä»£è¡¨åĽ¢
    -0.08
     cher
    -0.08
    æ¹İ
    -0.08
    éĻ¢éķ¿
    -0.08
    Ds
    -0.08
    è¿Ń
    -0.08
    é«ĺåħ´
    -0.08
    æĥ³çĿĢ
    -0.07
    <?,
    -0.07
    POSITIVE LOGITS
    Fax
    0.11
     бÑĥм
    0.11
    ä¼łçľŁ
    0.10
    é¹ŀ
    0.09
     Fax
    0.09
     fax
    0.09
    绪
    0.09
    建åįİ
    0.09
     Isles
    0.08
    ä¸īåįĥ
    0.08
    Activations Density 0.012%

    No Known Activations