© 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. 23607
    Prev
    Next
    INDEX
    Explanations

    finance or technology vocabulary

    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
    è¦ģä¹Ī
    -0.07
    onta
    -0.07
     usual
    -0.07
    æīĭ头
    -0.07
    åľ¨åIJĮä¸Ģ
    -0.07
     либо
    -0.07
    åģĩå®ļ
    -0.06
    以为
    -0.06
     unless
    -0.06
    antro
    -0.06
    POSITIVE LOGITS
    çļĦ大éĩı
    0.08
    hé
    0.08
    产åĵģçļĦçłĶåıij
    0.08
    åħļå§Ķåī¯ä¹¦è®°
    0.08
    zac
    0.08
    _tD
    0.08
    ÑģаÑĢ
    0.08
    γκα
    0.08
    ä¸ŃçļĦåºĶçĶ¨
    0.07
    [href
    0.07
    Activations Density 0.006%

    No Known Activations