© 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. 65345
    Prev
    Next
    INDEX
    Explanations

    equilateral triangle

    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
    enson
    -0.07
    ód
    -0.07
    çŀĴ
    -0.07
    ouv
    -0.07
    éz
    -0.06
    ÑĤаж
    -0.06
    èĤ¤
    -0.06
    orpion
    -0.06
    å¿ħ
    -0.06
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.06
    POSITIVE LOGITS
    æ¯ıç§Ĵ
    0.08
    chip
    0.07
    è´¨éĩı好
    0.07
     approximate
    0.07
    apers
    0.07
    æľīç͍
    0.07
    prime
    0.07
    åľ°åĪ©
    0.07
    åij¨åĽ´çļĦ人
    0.07
     lähellä
    0.07
    Activations Density 0.002%

    No Known Activations