© 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. 39111
    Prev
    Next
    INDEX
    Explanations

    another day

    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
    äºijéĽĨ
    -0.10
    åIJĥå¾Ĺ
    -0.09
    achen
    -0.09
     Fare
    -0.08
     fare
    -0.08
    latex
    -0.08
    åįģä¸īå±Ĭ
    -0.08
    ä¸Ģåı£
    -0.08
    ä¸Ģä¸ĭåŃIJ
    -0.08
    èĮħ
    -0.08
    POSITIVE LOGITS
    æ¯ıä¸Ģ天
    0.16
    ä¸Ģ天
    0.13
    æĸ°çļĦä¸Ģ
    0.13
    æĹ¥å¸¸çĶŁæ´»
    0.12
    æĹ©æĻ¨
    0.11
    æ¯ıæĹ¥
    0.11
     daily
    0.11
    æ¯ı天
    0.11
     mornings
    0.10
    æĻ¨
    0.10
    Activations Density 0.064%

    No Known Activations