© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    cdot multiplication symbole

    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
    çļĦæĺ¯
    -0.07
    ielo
    -0.07
    _KEYBOARD
    -0.06
    çĮ
    -0.06
     deles
    -0.06
    doi
    -0.06
    ä¹ĭ交
    -0.06
    alysis
    -0.06
    1
    -0.06
    }?
    -0.06
    POSITIVE LOGITS
    plication
    0.07
    ä¼ļåĦ¿
    0.07
    anton
    0.07
    æ¯ĵ
    0.07
    æĻ®åĪ©
    0.07
    çİ¥
    0.07
    麼
    0.07
    æĤ¨æīĢ
    0.07
    転
    0.06
    ÅĽ
    0.06
    Activations Density 0.006%

    No Known Activations