© 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. 20079
    Prev
    Next
    INDEX
    Explanations

    F.ley, my.ilton, Stilton Jarlsberg

    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
    abin
    -0.09
    æī¿åıĹ
    -0.09
    ç½ĺ
    -0.09
    è¿Ļåıªæĺ¯
    -0.08
    ä¸ºæł¸å¿ĥçļĦ
    -0.08
    .freeze
    -0.08
    Foundation
    -0.08
    人寿
    -0.08
     frost
    -0.08
    æĿĪ
    -0.08
    POSITIVE LOGITS
    ugs
    0.09
    -Aug
    0.08
    æ¡ĮåŃIJä¸Ĭ
    0.08
    ç§ij
    0.08
    _mB
    0.08
    keit
    0.08
    eker
    0.08
    à²ķ
    0.08
    ame
    0.08
    INK
    0.08
    Activations Density 0.115%

    No Known Activations