© 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. 13400
    Prev
    Next
    INDEX
    Explanations

    math formulas and code symbols

    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
    eps
    -0.07
     Gord
    -0.07
    ep
    -0.07
    åį³åĪ°
    -0.07
    æµĴ
    -0.07
    失败
    -0.06
    åĮ»éĻ¢è¿Ľè¡Į
    -0.06
    èĥĮ
    -0.06
    æĪij们éĥ½ä¼ļ
    -0.06
    æĹłæķĮ
    -0.06
    POSITIVE LOGITS
    alos
    0.08
    еÑħа
    0.08
    aksin
    0.07
     rather
    0.07
    orn
    0.07
     BEFORE
    0.07
    [...,
    0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    0.07
    两项
    0.07
    åķĨçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations