© 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. 2966
    Prev
    Next
    INDEX
    Explanations

    non-english characters and code syntax

    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
    undu
    -0.08
    å¦Ĥæľī
    -0.08
    å¦ĤæŀľéľĢè¦ģ
    -0.07
    ä¿ĿæĮģèī¯å¥½çļĦ
    -0.07
    好åIJĹ
    -0.07
    å¦ĤéľĢ
    -0.07
    .xhtml
    -0.07
    ardia
    -0.07
    گرÛĮ
    -0.07
    undi
    -0.06
    POSITIVE LOGITS
    tyw
    0.07
    ossal
    0.07
    æ®ĸæ°ijåľ°
    0.07
    亮起
    0.06
    ç«ĭå¾·
    0.06
    беÑĤ
    0.06
    åd
    0.06
    åĴĮä½ľçĶ¨
    0.06
    -Allow
    0.06
    ây
    0.06
    Activations Density 0.109%

    No Known Activations