© 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. 9605
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    [array
    -0.08
    .Features
    -0.07
    uss
    -0.07
    aro
    -0.07
    emo
    -0.07
    æĦŁ
    -0.06
    ife
    -0.06
    åŃ¦ä¹łåĪ°
    -0.06
    åħļ代ä¼ļ
    -0.06
    an
    -0.06
    POSITIVE LOGITS
    Enlarge
    0.08
    .PNG
    0.08
     orto
    0.08
    clipboard
    0.07
    åĴĮç½ij绾
    0.07
    uges
    0.07
    JPEG
    0.07
    /tab
    0.07
    æ§Ľ
    0.07
    tait
    0.07
    Activations Density 0.042%

    No Known Activations