© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    a variable declaration

    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
    æĢĢçĿĢ
    -0.09
    峡
    -0.08
    aldi
    -0.08
    Ñĩе
    -0.08
    è¡Ĺä¸Ĭ
    -0.08
     Paperback
    -0.08
    ä¸įæĸŃçļĦ
    -0.08
    ERP
    -0.08
    èļĵ
    -0.07
    å½¼
    -0.07
    POSITIVE LOGITS
    ively
    0.12
    æĪĸèĢħ说
    0.11
    è¦ģ说
    0.10
    çĦ¶æĺ¯
    0.09
    çĭIJ
    0.09
    atively
    0.09
    è¿Ļ个ä¸ĸçķĮ
    0.09
    weeney
    0.09
    elling
    0.09
    æľīéĹľ
    0.09
    Activations Density 0.251%

    No Known Activations