© 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. 27414
    Prev
    Next
    INDEX
    Explanations

    game genres and mechanics

    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
    æ®Ĭ
    -0.09
    ä¸Ģå¼ł
    -0.09
    åįĥæĸ¹çĻ¾è®¡
    -0.09
    æĹłåı¯
    -0.09
    æ¯ħ
    -0.09
    è£ħæī®
    -0.09
    berger
    -0.09
    ÑīиÑĤ
    -0.08
    åı¯æĥ³
    -0.08
    trail
    -0.08
    POSITIVE LOGITS
    çĿ£
    0.09
    dap
    0.09
    æĪIJè¯Ń
    0.09
    夸大
    0.09
    æ±Ĺæ°´
    0.09
    å¤¸å¼ł
    0.09
     Gore
    0.08
     exagger
    0.08
    éĺµ
    0.08
    CustomAttributes
    0.08
    Activations Density 0.120%

    No Known Activations