© 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. 61542
    Prev
    Next
    INDEX
    Explanations

    Oh what

    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
    crow
    -0.09
    inters
    -0.09
    梦幻
    -0.09
     Zw
    -0.09
    chal
    -0.09
    ä¸Ģç«Ļ
    -0.09
    éĥ¨éķ¿
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    TRL
    -0.08
    举é£İ
    -0.08
    POSITIVE LOGITS
    éĤ£å°±
    0.13
    éļ¾æĢª
    0.13
    éĤ£ä½ł
    0.12
    çŁ¥éģĵäºĨ
    0.11
    è¿Ļå°±
    0.10
    æĺİçĻ½äºĨ
    0.10
    è¿Ļä¹Ł
    0.09
     then
    0.09
    ote
    0.08
    éĤ£ä¹Ī
    0.08
    Activations Density 0.037%

    No Known Activations