© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36675
    Prev
    Next
    INDEX
    Explanations

    games won or lost

    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¸Ģè¾ĪåŃIJ
    -0.09
    åħ¨å¹´
    -0.09
    年度
    -0.08
    æīĵåį°æľº
    -0.08
    æľĢç»Ī
    -0.08
    ä»°
    -0.08
    1
    -0.08
    åĨľåľº
    -0.08
    çĪ·
    -0.08
    ogo
    -0.08
    POSITIVE LOGITS
    åĪ°çİ°åľ¨
    0.10
    alom
    0.10
    é¾Ħ
    0.10
    .games
    0.10
    寸
    0.09
    _already
    0.09
    wers
    0.09
    ä»ĸå·²ç»ı
    0.09
    ãģ£ãģ¦ãģĦãģ¾ãģĻ
    0.09
    ä¸įæĿ¥
    0.09
    Activations Density 0.040%

    No Known Activations