© 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. 31230
    Prev
    Next
    INDEX
    Explanations

    gel, matte, cleans, DOCTYPE, class, ac

    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
    skin
    -0.09
     skin
    -0.09
    åı£è¢ĭ
    -0.09
    é¢Ī
    -0.09
    DN
    -0.08
    Skin
    -0.08
    _skin
    -0.08
     Skin
    -0.08
    çļ®èĤ¤
    -0.08
    shade
    -0.08
    POSITIVE LOGITS
    è¿Ļæĸ¹éĿ¢
    0.11
    说æĪij
    0.10
    æĤ¬å´ĸ
    0.10
    被æįķ
    0.09
    æķ´é½IJ
    0.09
    综èīº
    0.09
    æ®ī
    0.09
    ãĥķãĤ¡ãĥ¼
    0.09
    .addChild
    0.09
    æĸĭ
    0.09
    Activations Density 0.024%

    No Known Activations