© 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. 60801
    Prev
    Next
    INDEX
    Explanations

    example

    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
    åħ¶
    -0.08
     anyhow
    -0.07
     anyway
    -0.07
    isine
    -0.07
    åħ¶çľŁå®ŀæĢ§
    -0.07
     thereof
    -0.07
    jsx
    -0.07
     therein
    -0.07
    åħ¶è¡Į为
    -0.07
     necessarily
    -0.07
    POSITIVE LOGITS
    å°±æĽ¾
    0.09
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    åIJĮæł·æĺ¯
    0.08
     halnya
    0.08
    常è§ģçļĦ
    0.07
     ìĸ´ëĸ¤
    0.07
    ìļĶ
    0.07
    vente
    0.07
    å½ĵãģ¦
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.042%

    No Known Activations