© 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. 9670
    Prev
    Next
    INDEX
    Explanations

    increasing to or by amounts

    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
    循
    -0.10
    è¿Ļ个æĹ¶ä»£
    -0.09
    urate
    -0.09
    åĩłå¼ł
    -0.08
    æ¯ķ
    -0.08
    zan
    -0.08
    ĥĿ
    -0.08
    讹
    -0.08
    à¸Ľà¸£à¸°
    -0.08
    é¢łè¦Ĩ
    -0.08
    POSITIVE LOGITS
    æĿ¥åĪ°
    0.09
    ç«Ļåľ¨
    0.09
    eland
    0.09
    _PS
    0.08
    åİ»
    0.08
    è´Ŀ壳
    0.08
     Gross
    0.08
     absolute
    0.08
    uing
    0.08
    ведиÑĤе
    0.07
    Activations Density 0.027%

    No Known Activations