© 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. 49344
    Prev
    Next
    INDEX
    Explanations

    news headlines and reports

    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
    积
    -0.07
    enius
    -0.07
    åŁºæĿIJ
    -0.07
    orest
    -0.07
    en
    -0.07
    ä¹ĥ
    -0.06
    æĨĶæĤ´
    -0.06
    enner
    -0.06
    ritable
    -0.06
    ilet
    -0.06
    POSITIVE LOGITS
    nitz
    0.08
    еп
    0.07
    avery
    0.07
    opa
    0.07
    åħ¬åı¸åijĺå·¥
    0.07
    就差
    0.07
    mue
    0.07
    berger
    0.07
    pars
    0.07
    ä¸įèµ·æĿ¥
    0.07
    Activations Density 0.001%

    No Known Activations