© 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. 58752
    Prev
    Next
    INDEX
    Explanations

    copyright claims

    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
    æĢ»å±Ģ
    -0.09
    ä¸Ģç«Ļ
    -0.09
    便
    -0.09
     ec
    -0.09
    豺
    -0.09
    澳洲
    -0.08
    çĴIJ
    -0.08
    éĺı
    -0.08
    åįİåĮĹ
    -0.08
    æĸ°åĬł
    -0.08
    POSITIVE LOGITS
     Tcl
    0.11
    æ¸Ŀ
    0.11
    king
    0.10
    è¯ĦåĪ¤
    0.09
    .tk
    0.09
    ä¸ī峡
    0.09
    綦
    0.09
    å¿«æĬ¥
    0.09
    ä¹į
    0.08
    centers
    0.08
    Activations Density 0.088%

    No Known Activations