© 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. 10575
    Prev
    Next
    INDEX
    Explanations

    game and games

    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
    éħį
    -0.11
    ä¸Ģ大æī¹
    -0.10
    æ®Ľ
    -0.09
    温åĴĮ
    -0.09
    飧
    -0.09
    éħįä¸Ĭ
    -0.09
    ioned
    -0.09
    ynn
    -0.09
    å½ķéŁ³
    -0.09
    èİł
    -0.09
    POSITIVE LOGITS
     game
    0.16
    游æĪıä¸Ń
    0.15
    游æĪı
    0.15
    è¿Ļ个游æĪı
    0.15
     games
    0.14
    GAME
    0.14
     GAME
    0.13
    该游æĪı
    0.13
    çĸ
    0.13
    游æĪıå½ĵä¸Ń
    0.13
    Activations Density 0.287%

    No Known Activations