© 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. 43700
    Prev
    Next
    INDEX
    Explanations

    `InstanceState`, `request`, `href`

    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
     Perdana
    -0.08
    راÙĨ
    -0.08
    éĿĵ
    -0.07
    çļĦèĥĮåIJİ
    -0.07
    auta
    -0.07
    lian
    -0.07
    让广大
    -0.07
    ([{
    -0.07
    Ùĩب
    -0.07
    $',
    -0.07
    POSITIVE LOGITS
    idor
    0.07
    adar
    0.07
    izzard
    0.06
    eth
    0.06
    iod
    0.06
    ä¸Ģä¸ĭå°±
    0.06
    imest
    0.06
     reb
    0.06
    ä¹Łå°±æĺ¯è¯´
    0.06
    izz
    0.06
    Activations Density 0.001%

    No Known Activations