© 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. 11151
    Prev
    Next
    INDEX
    Explanations

    DuckDuckGo, University, left(

    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
     deteri
    -0.08
    é«ĺéĽĦ
    -0.07
    antas
    -0.07
    å¦ĤæѤ
    -0.07
    herent
    -0.07
    riqu
    -0.07
    æĺ¯å¦ĤæѤ
    -0.07
    zl
    -0.07
     глÑĥби
    -0.07
    ropic
    -0.07
    POSITIVE LOGITS
    åı·
    0.06
     diss
    0.06
    ä¸ĢåĬ¨
    0.06
    鸯
    0.06
    åı·ä¸º
    0.06
    æľŁåĴĮ
    0.06
    åĿIJåĪ°
    0.06
    ائÙģ
    0.06
    åı·åĴĮ
    0.06
     Cama
    0.06
    Activations Density 0.002%

    No Known Activations