© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20654
    Prev
    Next
    INDEX
    Explanations

    send mail function

    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
    oire
    -0.10
    温åĴĮ
    -0.09
    ä¸įäºĨ
    -0.09
    åĩºå±Ģ
    -0.09
    å¸Ń
    -0.09
    ارد
    -0.09
    eated
    -0.09
     SYNC
    -0.09
     ÙħÙħا
    -0.09
    oine
    -0.08
    POSITIVE LOGITS
    æģ¯
    0.10
     liá»ĩu
    0.08
    fox
    0.08
    2
    0.08
     Tip
    0.08
    æ¶İ
    0.08
    nee
    0.08
    1
    0.08
    èĻļå¼±
    0.08
    egin
    0.08
    Activations Density 0.001%

    No Known Activations