© 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. 18538
    Prev
    Next
    INDEX
    Explanations

    legal sections and codes

    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
    éĥ½æĺ¯èĩªå·±
    -0.08
    strup
    -0.07
    inaire
    -0.07
    .getAbsolutePath
    -0.07
    ÙĤا
    -0.07
    æĴ²
    -0.07
    quir
    -0.07
    ulut
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    aldi
    -0.07
    POSITIVE LOGITS
    æĿ¡æĸĩ
    0.09
     Chambers
    0.07
     положениÑı
    0.07
     amended
    0.07
    actus
    0.07
     quoted
    0.07
    дей
    0.07
    è§Ħå®ļäºĨ
    0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    0.07
     as
    0.07
    Activations Density 0.054%

    No Known Activations