© 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. 36590
    Prev
    Next
    INDEX
    Explanations

    Drake, ford, driver, rake

    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
    å¨ĥå¨ĥ
    -0.09
    leck
    -0.09
    æľĭ
    -0.09
    ãĤĮ
    -0.08
    ieu
    -0.08
    æĽ¹
    -0.08
    _ARB
    -0.08
    ç²ij
    -0.08
     Fargo
    -0.08
    naire
    -0.08
    POSITIVE LOGITS
    åĽŀäºĭ
    0.10
    ford
    0.09
    болÑĮ
    0.09
    isha
    0.09
    ä¸įåĩºæĿ¥
    0.08
    å¹³åĿĩæ°´å¹³
    0.08
    manship
    0.08
    intosh
    0.08
    ого
    0.08
    eur
    0.08
    Activations Density 0.002%

    No Known Activations