© 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. 18219
    Prev
    Next
    INDEX
    Explanations

    div and panel contents

    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
    _EXT
    -0.07
    åĻĮ
    -0.07
    _EXTENSIONS
    -0.07
    astre
    -0.07
    áĢ¶
    -0.07
    缴æİ¥å°Ĩ
    -0.07
    éħįç½®
    -0.07
    å±¹
    -0.06
    Ext
    -0.06
    ä¹ĭ忧
    -0.06
    POSITIVE LOGITS
    åĮºåŁŁåĨħçļĦ
    0.09
    åĮºåŁŁåĨħ
    0.09
    åĮºåĨħ
    0.09
    ä¸Ĭå½ĵ
    0.08
     localVar
    0.08
     confines
    0.08
    _contents
    0.08
     confined
    0.08
    åįĢåŁŁ
    0.07
    åĮºåŁŁçļĦ
    0.07
    Activations Density 0.110%

    No Known Activations