© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6964
    Prev
    Next
    INDEX
    Explanations

    Insider / Slate websites

    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
    ãģ¥
    -0.10
     carriers
    -0.09
     ramp
    -0.09
    ×ij×Ĺ
    -0.09
    éĢļåijĬ
    -0.09
    Ùħج
    -0.09
    év
    -0.09
    ç½²
    -0.08
    linky
    -0.08
    欧å¼ı
    -0.08
    POSITIVE LOGITS
    æ»ĭ润
    0.09
    æĪIJç«ĭ
    0.09
    éĤ£æ®µ
    0.09
    oola
    0.08
    ä¸ĢæīĢ
    0.08
    ameda
    0.08
    åĢ¬
    0.08
    IAL
    0.08
    æĿłæĿĨ
    0.08
    è¿ĩåī©
    0.08
    Activations Density 0.005%

    No Known Activations