© 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. 60745
    Prev
    Next
    INDEX
    Explanations

    navbar and header components

    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
    åºĬä¸Ĭ
    -0.07
    lez
    -0.06
    å¹³åľ°
    -0.06
    宫èħĶ
    -0.06
    åľ°ä¸ĬçļĦ
    -0.06
    ä¸įè¿ľ
    -0.06
    spr
    -0.06
     Cardi
    -0.06
     patch
    -0.06
    身ä¸Ĭ
    -0.06
    POSITIVE LOGITS
     navigation
    0.09
    _navigation
    0.09
    /sidebar
    0.08
    DrawerToggle
    0.08
    idebar
    0.08
    header
    0.08
    /header
    0.08
     sider
    0.08
    HEADER
    0.08
    导èĪª
    0.08
    Activations Density 0.178%

    No Known Activations