© 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. 34658
    Prev
    Next
    INDEX
    Explanations

    code keywords and 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
    apte
    -0.07
    פר
    -0.07
    umpa
    -0.07
    ಳ
    -0.07
    alling
    -0.07
    pla
    -0.07
    ãģ¤ãģĭ
    -0.07
    erche
    -0.07
    umé
    -0.07
    été
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    å¤ľçļĦ
    0.06
    æ½
    0.06
    åĪĨéĴŁåīį
    0.06
    æŃ¢
    0.06
    endregion
    0.06
    æĹłç¼ĺ
    0.06
     Anim
    0.06
    å®ĮäºĨ
    0.06
    éĩįéĩįçļĦ
    0.06
    Activations Density 0.274%

    No Known Activations