© 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. 61323
    Prev
    Next
    INDEX
    Explanations

    opening parentheses

    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
    ossi
    -0.08
    æľĶ
    -0.07
     pula
    -0.07
    çļĦ缮çļĦ
    -0.07
    主ä½ĵçļĦ
    -0.07
    缮çļĦ
    -0.07
    (?)
    -0.07
    ä¹ĭ缮çļĦ
    -0.07
    ãĨ
    -0.06
    ogos
    -0.06
    POSITIVE LOGITS
    æİ¥ä¸ĭ
    0.08
     Doch
    0.07
    евÑģкого
    0.07
    åĿļå®ļäºĨ
    0.07
    lemn
    0.07
    IFT
    0.07
    _Private
    0.07
    éĺģ楼
    0.07
    æĬ¤çIJĨå·¥ä½ľ
    0.07
    vera
    0.07
    Activations Density 0.012%

    No Known Activations