© 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. 27858
    Prev
    Next
    INDEX
    Explanations

    working hard and diligently

    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
     ÑĥÑĩаÑģÑĤие
    -0.09
    åıªéľĢ
    -0.09
    人家
    -0.08
    寺
    -0.08
    atron
    -0.08
    .reporting
    -0.08
    é«ĺ度éĩįè§Ĩ
    -0.08
    éĤĢ
    -0.08
    Äĸ
    -0.08
    ugs
    -0.08
    POSITIVE LOGITS
    åħ¢
    0.09
    èĤ´
    0.09
    æĹ¥å¤ľ
    0.09
    å¿ĻçĿĢ
    0.09
    ä¸įåģľ
    0.09
     rou
    0.09
    æĺ¼å¤ľ
    0.09
    _codec
    0.08
    æĬ¢æķij
    0.08
     pep
    0.08
    Activations Density 0.025%

    No Known Activations