© 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. 49393
    Prev
    Next
    INDEX
    Explanations

    announcement made

    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
    inde
    -0.10
    elsen
    -0.09
     окол
    -0.09
    ::__
    -0.08
    纵
    -0.08
    çļĦç¡®æĺ¯
    -0.08
    Whats
    -0.08
    åĭ¤
    -0.08
    ,__
    -0.08
     stere
    -0.08
    POSITIVE LOGITS
    åŃª
    0.11
    æĿ¥æºIJäºİ
    0.11
    æĿ¥èĩªäºİ
    0.10
    uju
    0.10
    æĺ¯åľ¨
    0.09
    มาà¸Īาà¸ģ
    0.09
    è¿ĻçĤ¹
    0.09
    çī¹äº§
    0.09
    çķ¥
    0.09
    æŃ»åIJİ
    0.09
    Activations Density 0.110%

    No Known Activations