© 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. 9354
    Prev
    Next
    INDEX
    Explanations

    code blocks ending with `}`

    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
    dach
    -0.08
    ä¸Ńåħ±åħļåijĺ
    -0.07
    avant
    -0.07
    ibun
    -0.07
    alsy
    -0.07
     awaiting
    -0.07
    attel
    -0.07
     astr
    -0.07
    eland
    -0.07
    shot
    -0.07
    POSITIVE LOGITS
    ä¸ī轮车
    0.07
    åĻ
    0.07
    讨
    0.07
    åĩĢ
    0.06
    åıĮé¾Ļ
    0.06
    ->_
    0.06
    管
    0.06
    ç¥Ł
    0.06
    ä¸īè½®
    0.06
    ä¸įèµ°
    0.06
    Activations Density 0.090%

    No Known Activations