© 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. 49095
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    æĸ°éĹ»ç½ij
    -0.08
    Ùħا
    -0.08
    _INITIALIZ
    -0.08
    缨
    -0.07
    彬
    -0.07
    移
    -0.07
    ktion
    -0.07
    ç¦ıæĺŁ
    -0.07
     Fuk
    -0.07
    illard
    -0.07
    POSITIVE LOGITS
    ieb
    0.08
    lieb
    0.07
    offee
    0.07
    га
    0.07
    èĢĺ
    0.06
    vény
    0.06
    unas
    0.06
    ConfigurationException
    0.06
    earer
    0.06
    nid
    0.06
    Activations Density 0.373%

    No Known Activations