© 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. 21019
    Prev
    Next
    INDEX
    Explanations

    tools, plugins, cart, tags, services

    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
    çIJĨ解äºĨ
    -0.07
    اÙħÙĬÙĨ
    -0.07
    檻
    -0.07
    بت
    -0.07
    øy
    -0.07
    è¯¥æľº
    -0.07
    解éĩĬäºĨ
    -0.07
    @s
    -0.07
    mozilla
    -0.07
    ithe
    -0.07
    POSITIVE LOGITS
    _proxy
    0.07
    å¼Ģå¾Ĺ
    0.07
    asty
    0.07
    輪
    0.07
     stamp
    0.07
    proxy
    0.06
    ä»»ä½ł
    0.06
     tar
    0.06
     proxy
    0.06
     Fowler
    0.06
    Activations Density 0.001%

    No Known Activations