© 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. 22350
    Prev
    Next
    INDEX
    Explanations

    sports and related activities

    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
    eday
    -0.10
    è°Ĺ
    -0.10
    æĶ
    -0.09
    æĻļæľŁ
    -0.09
    obo
    -0.09
    ä¸IJ
    -0.08
    å±ij
    -0.08
    é¦ĭ
    -0.08
    ncy
    -0.08
    itet
    -0.08
    POSITIVE LOGITS
    æ´»åĬ¨
    0.14
     activities
    0.13
    æ´»åĭķ
    0.12
    室å¤ĸ
    0.12
    èĩªå·±åĸľæ¬¢
    0.12
     Recreation
    0.11
    ä¸Ģ项
    0.11
    æ´»åĬ¨çİ°åľº
    0.11
     recre
    0.11
    Activities
    0.11
    Activations Density 0.061%

    No Known Activations