© 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. 47723
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and characters

    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
    ä¸įæĺ¯ä»Ģä¹Ī
    -0.07
    æķĻèĤ²å·¥ä½ľ
    -0.07
    oki
    -0.06
    ä¸įæĺ¯è¯´
    -0.06
    ابÛĮ
    -0.06
    oyo
    -0.06
    ureau
    -0.06
    åѦçĶŁçļĦåŃ¦ä¹ł
    -0.06
     Isab
    -0.06
    s
    -0.06
    POSITIVE LOGITS
    fet
    0.08
    绣
    0.07
    occas
    0.07
    hci
    0.07
     **:**
    0.07
    autorelease
    0.07
    áĢĶáĢºáĢ¸
    0.07
    å°¤åħ¶æĺ¯
    0.07
    виа
    0.07
    è¡·å¿ĥçļĦ
    0.06
    Activations Density 0.030%

    No Known Activations