© 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. 21578
    Prev
    Next
    INDEX
    Explanations

    playing with

    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
     Marin
    -0.10
    沸èħ¾
    -0.09
    loe
    -0.09
    满èĦ¸
    -0.08
    cot
    -0.08
     Lomb
    -0.08
    omin
    -0.08
     Lou
    -0.08
    ä¿®è¡Į
    -0.08
    ses
    -0.08
    POSITIVE LOGITS
    éŀŃ
    0.09
    ä¸İä¼Ĺ
    0.09
    æ¡Į
    0.08
     divert
    0.08
    éĢIJ
    0.08
    ä¸Ģä¼ļ
    0.08
    æ¡ĮåŃIJ
    0.08
     Faul
    0.08
    VIDEO
    0.08
    ä¸įæĪIJ
    0.08
    Activations Density 0.027%

    No Known Activations