© 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. 31534
    Prev
    Next
    INDEX
    Explanations

    physics and geometry

    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
    çĽ²
    -0.08
    lisi
    -0.08
    akers
    -0.08
    doa
    -0.08
     cục
    -0.08
    strup
    -0.07
    æľ¬åľ°åĮº
    -0.07
    æ³ī
    -0.07
     Quell
    -0.07
    aker
    -0.07
    POSITIVE LOGITS
     electron
    0.07
     circumference
    0.07
     Classical
    0.07
    ç¼Ŀ
    0.07
    æį®è¯´
    0.07
     Fixes
    0.07
    åł°
    0.07
    arrer
    0.07
    çİ°åľ¨çľĭæĿ¥
    0.06
    tac
    0.06
    Activations Density 0.001%

    No Known Activations