© 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. 25373
    Prev
    Next
    INDEX
    Explanations

    Lambda(c) decays

    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
     Pyongyang
    -0.09
    åĩ¡
    -0.08
    ornado
    -0.08
    ç¿°æŀĹ
    -0.07
    /article
    -0.07
    eor
    -0.07
    icals
    -0.07
    /activity
    -0.07
    urve
    -0.07
    éħ£
    -0.07
    POSITIVE LOGITS
     Dagger
    0.07
    unos
    0.07
    енÑģи
    0.07
    족
    0.07
     pén
    0.07
    é«ĺåİŁ
    0.07
    ìļ´
    0.06
    西å®ģ
    0.06
    å¼ķè¿Ľ
    0.06
    ugh
    0.06
    Activations Density 0.006%

    No Known Activations