© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23265
    Prev
    Next
    INDEX
    Explanations

    distance or location

    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
    chine
    -0.09
    ÅĽni
    -0.08
    vrier
    -0.08
    áĭ«
    -0.07
    iony
    -0.07
    blatt
    -0.07
    Ø«ÙĨ
    -0.07
    å¿ĥçĶĺ
    -0.07
    æľīåij³
    -0.07
    åįİéĺ³
    -0.07
    POSITIVE LOGITS
     distant
    0.09
    天边
    0.08
    è¿ľæĸ¹
    0.08
    è¿ľ
    0.08
    éģĻ
    0.08
     infinite
    0.07
    è¿ľçļĦ
    0.07
     afar
    0.07
    éģ¥
    0.07
    æ·¡
    0.07
    Activations Density 0.001%

    No Known Activations