© 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. 53112
    Prev
    Next
    INDEX
    Explanations

    soccer and other sports positions

    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
    御
    -0.11
    lle
    -0.09
    ÑīиÑĤ
    -0.08
    же
    -0.08
    diet
    -0.08
    Õ±
    -0.08
    ile
    -0.08
    dio
    -0.08
    dorf
    -0.08
    ected
    -0.08
    POSITIVE LOGITS
    人éĢī
    0.10
    egin
    0.08
    oggles
    0.08
     Loft
    0.08
    _ABI
    0.08
    èĦĤèĤª
    0.08
    IVO
    0.08
    æģ£
    0.08
    ç²¾ç¥ŀçĹħ
    0.08
    _SAN
    0.08
    Activations Density 0.006%

    No Known Activations