© 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. 39084
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
    è®°èĢħåľ¨
    -0.10
    зн
    -0.09
    åĿIJåľ¨
    -0.09
    entr
    -0.08
    éĽĨä¸Ńåľ¨
    -0.08
    贯穿
    -0.08
    åľ¨è·¯ä¸Ĭ
    -0.08
    è¶´åľ¨
    -0.08
    æ¯ĶåĪĨ
    -0.08
     entr
    -0.08
    POSITIVE LOGITS
    åıijå±ķæĪĺçķ¥
    0.11
    åģļäºĭ
    0.10
    åħľ
    0.09
    ãģ¦ãģĦ
    0.09
    ä»»èģĮ
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    andi
    0.08
    ä»»æķĻ
    0.08
    è¿ĻæĶ¯
    0.08
    æıIJä¾ĽçļĦ
    0.08
    Activations Density 0.140%

    No Known Activations