© 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. 18653
    Prev
    Next
    INDEX
    Explanations

    sports team general manager

    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
    æľ¬ç½ij
    -0.11
    çļĦéģĵçIJĨ
    -0.10
    人å±ħ
    -0.10
    以éĺ²
    -0.10
    å½Ĵå±ŀäºİ
    -0.09
    ç½²
    -0.09
    æ··åĩĿ
    -0.09
    åĤ¥
    -0.09
    æ¶İ
    -0.09
    æľ¬æľŁ
    -0.09
    POSITIVE LOGITS
     getModel
    0.09
    çIJ¯
    0.09
    æĢª
    0.09
    窥
    0.08
     ster
    0.08
    ERN
    0.08
    à¤
    0.08
     topping
    0.08
     THROW
    0.08
    Cad
    0.08
    Activations Density 0.161%

    No Known Activations