© 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. 34024
    Prev
    Next
    INDEX
    Explanations

    computational dynamics simulations

    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
    æļĤ
    -0.10
    æĭįæĭį
    -0.09
    éĹ®éĹ®
    -0.09
    åľ¨çİ°åľº
    -0.09
    æļĤæŶ
    -0.09
    alu
    -0.09
     conv
    -0.08
    æĴ¸
    -0.08
    æļ«
    -0.08
    ç«ĭãģ¡
    -0.08
    POSITIVE LOGITS
    elry
    0.09
    Animations
    0.08
    çĶ¨æ°´
    0.08
    模æĭŁ
    0.08
    iddles
    0.08
    rimp
    0.08
    мол
    0.08
    补水
    0.08
    dock
    0.08
     kcal
    0.08
    Activations Density 0.591%

    No Known Activations