© 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. 35975
    Prev
    Next
    INDEX
    Explanations

    MGM, casinos, gaming machines

    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
    ä¸ŃåĽ½åĪ¶éĢł
    -0.09
    èŃ
    -0.09
    çļĦä½ľåĵģ
    -0.09
    åĮ£
    -0.09
    å¯Ĵ
    -0.09
     pop
    -0.08
    èĻ
    -0.08
    侦æİ¢
    -0.08
    .nlm
    -0.08
    æĭ¿äºĨ
    -0.08
    POSITIVE LOGITS
    æ´ŀ
    0.09
    Ñģко
    0.09
    æīĵåĩº
    0.09
    åįĵ
    0.08
    .Strict
    0.08
    æĹ¥åŃIJ
    0.08
     Richards
    0.08
     Rac
    0.08
    imbus
    0.08
    æIJĵ
    0.08
    Activations Density 0.014%

    No Known Activations