© 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. 22899
    Prev
    Next
    INDEX
    Explanations

    foreign names and places with apostrophes

    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
    atas
    -0.08
    awe
    -0.07
    à§įতà§ģ
    -0.07
    Ñĩини
    -0.07
    imai
    -0.07
    acam
    -0.07
    arahan
    -0.07
    acea
    -0.07
    enen
    -0.07
    DeviceInfo
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.11
    ï¸İ
    0.09
    äºĭåįĬåĬŁåĢį
    0.08
    俱ä¹IJéĥ¨
    0.07
    ÙĩÙı
    0.07
    å¬Ľ
    0.07
    ¤
    0.07
     abbast
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    çĤ¹åĩ»å¤įåĪ¶éĵ¾æİ¥
    0.06
    Activations Density 0.142%

    No Known Activations