© 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. 43824
    Prev
    Next
    INDEX
    Explanations

    yellow chunk

    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
    åĢ¾
    -0.08
    fle
    -0.08
     Quay
    -0.07
    _CAL
    -0.07
    ts
    -0.07
    /]
    -0.06
    /react
    -0.06
    io
    -0.06
    丽ä¸Ŀ
    -0.06
     viss
    -0.06
    POSITIVE LOGITS
    æķ·
    0.09
     `"
    0.08
     `'
    0.08
     ![
    0.07
    åľ¨æľ¬ç«Ļ
    0.07
    ¡´
    0.07
    umat
    0.07
    è§ģéĻĦ件
    0.07
    裹
    0.07
    à¹īà¸Ńà¸Ļ
    0.07
    Activations Density 0.008%

    No Known Activations