© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 34309
    Prev
    Next
    INDEX
    Explanations

    coordinates and geometric points

    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
    强弱
    -0.09
    embang
    -0.08
    .fn
    -0.08
    WORDS
    -0.08
    åĽ´ç»ķçĿĢ
    -0.07
    ëĦĪ
    -0.07
    _configs
    -0.07
    ç§įç±»ç¹ģå¤ļ
    -0.07
    è¿ĻæĿ¡è·¯
    -0.07
     Äijun
    -0.07
    POSITIVE LOGITS
     coordinates
    0.14
     Coordinates
    0.12
    åĿIJæłĩ
    0.12
    Coordinates
    0.12
    coordinates
    0.11
    -coordinate
    0.11
     coords
    0.10
     coordinate
    0.09
    ä½įç½®
    0.08
     coordonnées
    0.08
    Activations Density 0.002%

    No Known Activations