© 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. 64443
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     }//
    -0.08
    ',(
    -0.07
    alc
    -0.07
    论åĿĽä¸Ĭ
    -0.07
    åIJijä»ĸ们
    -0.07
    å®īå®ģ
    -0.06
    ä¸Ģä¼ļåĦ¿
    -0.06
    æĿ¥äºº
    -0.06
    .$.
    -0.06
    æĺİæĹ¥
    -0.06
    POSITIVE LOGITS
    ×Ĺ×ķת
    0.08
    ÙĪاب
    0.07
    æľĶ
    0.07
    ellini
    0.07
    uche
    0.07
    uchen
    0.07
    naie
    0.07
    建平
    0.06
    å±¥
    0.06
     belas
    0.06
    Activations Density 0.091%

    No Known Activations