© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58360
    Prev
    Next
    INDEX
    Explanations

    conditions leading to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻIJäºİ
    -0.09
    íķĺëĭĪ
    -0.08
    夫æĸ¯åŁº
    -0.08
    èĭ¥æĹł
    -0.08
    Enumerator
    -0.08
    ëij¥
    -0.07
     наÑģÑĤÑĢоениÑı
    -0.07
    »
    -0.07
    æĹ¥æŃ£å¼ı
    -0.07
     vần
    -0.07
    POSITIVE LOGITS
    ä¹Łè¢«ç§°ä¸º
    0.07
    enet
    0.07
     often
    0.06
     because
    0.06
    æĺ¯è¦ģ
    0.06
    æ³ķæĺ¯
    0.06
     perché
    0.06
     lære
    0.06
    lement
    0.06
    ka
    0.06
    Activations Density 0.004%

    No Known Activations