© 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. 43624
    Prev
    Next
    INDEX
    Explanations

    Apple, electronic, Dan, On

    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
    ipur
    -0.06
    ewise
    -0.06
    urst
    -0.06
    æ¥ļæ¥ļ
    -0.06
    ä¸įè§ī
    -0.05
    }$/
    -0.05
    egd
    -0.05
    é£İåIJ¹
    -0.05
    ecem
    -0.05
     “
    -0.05
    POSITIVE LOGITS
    ä¸ĸåįļä¼ļ
    0.07
    rotch
    0.06
    头
    0.06
    ÙĬدة
    0.06
    vaard
    0.06
    æ·¼
    0.06
    .ua
    0.06
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.06
    à²Ń
    0.06
    acz
    0.06
    Activations Density 0.076%

    No Known Activations