© 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. 48863
    Prev
    Next
    INDEX
    Explanations

    URL components like `www.`, `http`, or `=`

    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
    /native
    -0.07
    iesen
    -0.07
    /bus
    -0.07
    Õ¡Õ£
    -0.07
    abad
    -0.07
    akat
    -0.07
    verläss
    -0.06
    驾
    -0.06
    æ§Ľ
    -0.06
    é§ķ
    -0.06
    POSITIVE LOGITS
    inkan
    0.07
    åħįè´¹åľ¨çº¿
    0.07
    èģĺ
    0.07
    ูà¸Ķ
    0.07
    alt
    0.07
    ì°¬
    0.07
    пÑĢÑı
    0.07
    à¸Ķ
    0.07
    æľīæĿĥ
    0.06
    ocht
    0.06
    Activations Density 0.003%

    No Known Activations