© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12334
    Prev
    Next
    INDEX
    Explanations

    game series or streaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    åIJĦ个æĸ¹éĿ¢
    -0.20
    æĺ¯ä»Ģä¹Īåij¢
    -0.20
    tower
    -0.19
    å¼ģ
    -0.19
    ë§ģ
    -0.19
    缮åīįæŃ£åľ¨
    -0.18
    opsis
    -0.18
    èĥĦ
    -0.18
    _requires
    -0.17
     Rosenstein
    -0.17
    POSITIVE LOGITS
     Mas
    0.20
    ::$_
    0.19
    ä¼Ļ
    0.19
     оÑĩеÑĢед
    0.19
    cala
    0.19
    aday
    0.19
    åľ»
    0.18
    째
    0.18
    éĻIJæľŁ
    0.18
    ÙĬرة
    0.18
    Activations Density 0.006%

    No Known Activations