© 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. 6782
    Prev
    Next
    INDEX
    Explanations

    new event or opening

    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
    ä¸įæĸŃæī©å¤§
    -0.09
    upy
    -0.09
    èį£èªī称åı·
    -0.09
    loh
    -0.08
    ç»Ī身
    -0.08
    åħ±åĴĮ
    -0.08
     Shorts
    -0.08
    çݰ代åĨľä¸ļ
    -0.08
     Ott
    -0.08
    èį¯ä¸ļ
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦ
    0.13
     новÑĭе
    0.11
    åĩºçĤī
    0.11
     новÑĭÑħ
    0.10
    åħķ
    0.10
    ä¸įä¹ħ
    0.10
    å¿ĥæĥħ
    0.09
    /new
    0.09
    å¸ĮæľĽå¤§å®¶
    0.09
    æĸ°æĬĢæľ¯
    0.09
    Activations Density 0.131%

    No Known Activations