© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37280
    Prev
    Next
    INDEX
    Explanations

    entire / whole

    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
    æĥ©æĪĴ
    -0.09
    éĽ¢ãĤĮ
    -0.09
    aul
    -0.09
    ette
    -0.09
    ç¥Ĺ
    -0.08
    -ending
    -0.08
    nea
    -0.08
    é«ĺãģĦ
    -0.08
    rica
    -0.08
    ä½Ĺ
    -0.08
    POSITIVE LOGITS
    heart
    0.12
     entire
    0.11
     heck
    0.10
    unger
    0.10
    åĽµ
    0.09
    æľĪä¸ĭ
    0.09
    æķ´ä¸ª
    0.09
    身å¿ĥ
    0.09
    ies
    0.09
    ombat
    0.09
    Activations Density 0.042%

    No Known Activations