© 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. 48871
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

    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
    åį¿
    -0.10
    NCY
    -0.10
    æİĤ
    -0.09
    ducted
    -0.08
    人åĿĩ
    -0.08
    ä¸įæĸŃæıIJé«ĺ
    -0.08
    ãĤ¢ãĥĭ
    -0.08
    size
    -0.08
    site
    -0.08
    sons
    -0.08
    POSITIVE LOGITS
    æĦŁè§īèĩªå·±
    0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    0.10
    éķ¿éķ¿
    0.10
    rita
    0.10
    LU
    0.09
    åIJķ
    0.09
    ä¸ĢåĪ»
    0.09
    头çļ®
    0.09
    æľīä¸Ģç§į
    0.09
    ä¸Ģèĩ´æĢ§
    0.09
    Activations Density 0.263%

    No Known Activations