© 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. 33447
    Prev
    Next
    INDEX
    Explanations

    sports leagues, teams, and events

    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
    vertis
    -0.10
    Advertisements
    -0.10
    otas
    -0.09
    hone
    -0.09
    å°ĸ
    -0.09
    èłķ
    -0.09
    aversal
    -0.08
    omon
    -0.08
    è··
    -0.08
    å°ıå§IJå§IJ
    -0.08
    POSITIVE LOGITS
     football
    0.12
    è¿IJåĬ¨åijĺ
    0.12
    è¹´
    0.12
    âļ½
    0.11
     ÙĦÙĥرة
    0.11
    篮çIJĥ
    0.11
    ä½ĵèĤ²
    0.10
    éĢĢå½¹
    0.10
     basketball
    0.10
    æīĵçIJĥ
    0.10
    Activations Density 0.210%

    No Known Activations