© 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. 23880
    Prev
    Next
    INDEX
    Explanations

    distance, angles, and depth

    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
    å¤ļ彩
    -0.06
     marty
    -0.06
    éĿ¢æľĿ
    -0.06
    lux
    -0.06
    æ¿Ģèį¡
    -0.06
    æĻ®ç½Ĺ
    -0.06
    大年
    -0.06
    engan
    -0.06
    Backend
    -0.06
     Rear
    -0.06
    POSITIVE LOGITS
     distance
    0.10
    unload
    0.09
    distance
    0.09
    åĪĪ
    0.09
    eyond
    0.09
     distances
    0.09
    çļĦè·Ŀ离
    0.09
    è¿ľç¦»
    0.08
    è·Ŀ离
    0.08
    _distances
    0.08
    Activations Density 0.013%

    No Known Activations