© 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. 50706
    Prev
    Next
    INDEX
    Explanations

    voltage, measurement, or code

    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
    utant
    -0.08
     vik
    -0.07
    ocat
    -0.07
    æĹĭåį³
    -0.07
    ELLE
    -0.07
    checked
    -0.07
    ç±ģ
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    ofile
    -0.07
     heavier
    -0.07
    POSITIVE LOGITS
    å®ļä½į
    0.07
    Ñģов
    0.07
    Amb
    0.07
    ishi
    0.07
    亲亲
    0.07
    apon
    0.07
    å®ļä½įäºİ
    0.06
     Amb
    0.06
     loc
    0.06
    ur
    0.06
    Activations Density 0.002%

    No Known Activations