© 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. 30166
    Prev
    Next
    INDEX
    Explanations

    with China

    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
    zik
    -0.10
    æķĻèĤ²åŁ¹è®Ń
    -0.09
     gul
    -0.08
    iae
    -0.08
    adero
    -0.08
    åı¤èĢģçļĦ
    -0.08
    éļıæĦı
    -0.08
     viá»ĩc
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    wc
    -0.08
    POSITIVE LOGITS
    æķĮ人
    0.10
    åı¦ä¸Ģä½į
    0.10
    æĿł
    0.10
    åīįæĿ¥
    0.09
    cth
    0.09
    .getStyle
    0.09
    亲çĪ±
    0.09
    ä¸ĭ游
    0.09
    æľªå©ļ
    0.09
    主治
    0.09
    Activations Density 0.170%

    No Known Activations