© 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. 23660
    Prev
    Next
    INDEX
    Explanations

    sports statistics and scores

    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
    å±ĭ
    -0.10
    ugu
    -0.08
    èĭŀ
    -0.08
    æĸ¹éĿ¢
    -0.08
    5
    -0.08
    3
    -0.07
    0
    -0.07
     tit
    -0.07
    åħ¶å®ĥ
    -0.07
    满æĦıçļĦ
    -0.07
    POSITIVE LOGITS
    åĴĮä»ĸçļĦ
    0.13
    /her
    0.13
    æľ¬äºº
    0.11
    年纪
    0.11
    身影
    0.11
    ä½ľä¸ºä¸ĢåIJį
    0.11
    é£İéĩĩ
    0.10
    paragus
    0.10
    åĽĽèĤ¢
    0.10
    SELF
    0.10
    Activations Density 0.300%

    No Known Activations