© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42298
    Prev
    Next
    INDEX
    Explanations

    modelelements and proportion

    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
    pati
    -0.07
    è¤
    -0.07
    ìĿij
    -0.07
    itest
    -0.06
    à¹Ģลยวà¹Īา
    -0.06
    å®Ĺ
    -0.06
     pinned
    -0.06
    .LoggerFactory
    -0.06
    Sprite
    -0.06
     JsonRequest
    -0.06
    POSITIVE LOGITS
    ä¸Ĭè¿ĩ
    0.08
    ª
    0.08
    rze
    0.08
    ekk
    0.07
    é¦Ĩéķ¿
    0.07
    ä¹ĭéĹ´çļĦçŁĽçĽ¾
    0.07
    åī¯éĥ¨éķ¿
    0.07
    Concept
    0.07
    Orange
    0.07
    æŁ¥æŁ¥
    0.07
    Activations Density 0.887%

    No Known Activations