© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50247
    Prev
    Next
    INDEX
    Explanations

    events and names

    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
    æĸ°ç¤¾
    -0.08
    èĢĮ代ä¹ĭ
    -0.08
    veille
    -0.08
    reja
    -0.08
    bote
    -0.08
    leigh
    -0.07
    çĻ»å½ķæŁ¥çľĭ
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    åĴĮ幸ç¦ı
    -0.07
    ק×Ļ
    -0.07
    POSITIVE LOGITS
    dac
    0.07
    ç¾ļ
    0.07
    ç³ľ
    0.06
    artin
    0.06
    ZX
    0.06
    æIJŃ
    0.06
    dap
    0.06
    ä¸ŃåĽ½å®¶
    0.06
    LA
    0.06
    èį¡
    0.06
    Activations Density 2.624%

    No Known Activations