© 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. 38562
    Prev
    Next
    INDEX
    Explanations

    go books, problemist, chess

    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
    uent
    -0.10
    åįİåįĹ
    -0.09
    æ°ijèIJ¥
    -0.09
    产ä¸ļåĽŃ
    -0.09
    梦è§ģ
    -0.08
    bk
    -0.08
    æŀģéĢŁ
    -0.08
    çĶ·åŃ©åŃIJ
    -0.08
    ety
    -0.08
    æĪĪ
    -0.08
    POSITIVE LOGITS
    SplitOptions
    0.09
    çĽĬ
    0.09
    /compiler
    0.09
     Ñĥд
    0.09
    éľİ
    0.09
    è¯¥æł¡
    0.09
    çīĮ
    0.09
    俱ä¹IJéĥ¨
    0.08
    åĬª
    0.08
     club
    0.08
    Activations Density 0.036%

    No Known Activations