© 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. 22610
    Prev
    Next
    INDEX
    Explanations

    programming code and equations

    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
    uff
    -0.07
    eldon
    -0.07
     nah
    -0.07
    antum
    -0.07
    urus
    -0.07
    ])/
    -0.07
    ombat
    -0.06
    段
    -0.06
    _GRE
    -0.06
    _BAD
    -0.06
    POSITIVE LOGITS
    ïque
    0.09
    lique
    0.08
    æĬ¥åijĬ书
    0.07
    صÙģ
    0.07
    æ±Ĥå®ŀ
    0.07
    lisi
    0.07
    iseau
    0.07
    (suite
    0.07
    णà¥Ģ
    0.06
    RTL
    0.06
    Activations Density 0.001%

    No Known Activations