© 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. 3891
    Prev
    Next
    INDEX
    Explanations

    know they will

    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
    åĴĮå¹³
    -0.10
    åı¯ä»¥çľĭåĩº
    -0.10
    ä¹Łè®¸æĺ¯
    -0.10
    icast
    -0.09
     thú
    -0.09
    ainen
    -0.09
    对å¤ĸ
    -0.09
    ä¸įçŁ¥ä¸įè§ī
    -0.09
    ä¸įç»ıæĦı
    -0.09
    åĽŀæĥ³
    -0.09
    POSITIVE LOGITS
    èĤ¯å®ļæĺ¯
    0.10
    èĤ¯å®ļä¼ļ
    0.09
    èĤ¯å®ļ
    0.09
    ä¹ıåĬĽ
    0.09
    纵
    0.09
    cname
    0.09
     Gaw
    0.08
     ÙĪØ£ÙĨ
    0.08
    enha
    0.08
    perf
    0.08
    Activations Density 0.160%

    No Known Activations