© 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. 23926
    Prev
    Next
    INDEX
    Explanations

    company or service provider

    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
     Builders
    -0.07
    åĴĮ使åij½
    -0.07
    .Mutable
    -0.07
    åĿļå®ŀçļĦ
    -0.07
    ä¸įæķĮ
    -0.06
     Alegre
    -0.06
    åĪĨ享åĪ°
    -0.06
     Candidates
    -0.06
    è¢«ä¾ĽåºĶåķĨ
    -0.06
    oops
    -0.06
    POSITIVE LOGITS
    é¢ģåıijçļĦ
    0.10
    åĩºåħ·çļĦ
    0.10
    -approved
    0.10
    认åı¯çļĦ
    0.09
    -sponsored
    0.08
    ovia
    0.08
    æīĢæıIJä¾Ľ
    0.07
     setempat
    0.07
    ç»ĻçļĦ
    0.07
    æıIJä¾ĽçļĦ
    0.07
    Activations Density 0.379%

    No Known Activations