© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2260
    Prev
    Next
    INDEX
    Explanations

    played by or plays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    iagnostics
    -0.23
    Occurred
    -0.22
    -ground
    -0.22
    çļĦç²¾ç¥ŀ
    -0.22
    FUL
    -0.22
    ems
    -0.22
    ind
    -0.21
    æĮ¹
    -0.21
    _algorithm
    -0.21
    æĢ§åĴĮ
    -0.21
    POSITIVE LOGITS
    äºĮ代
    0.24
    erox
    0.21
     playwright
    0.21
    è¿ŀ线
    0.21
    iola
    0.21
    æ¼Ķåijĺ
    0.21
    å½ĵãģ¦
    0.21
    èĭ¥æľī
    0.20
     ëĮĢíĨµ
    0.20
    Train
    0.20
    Activations Density 0.023%

    No Known Activations