© 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. 47207
    Prev
    Next
    INDEX
    Explanations

    Copyright statements

    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
    è¿ľæµģ
    -0.07
    ingar
    -0.07
    å¥½å·¥ä½ľ
    -0.07
    åīĶéĢı
    -0.07
    çľĭåľ¨
    -0.07
    åıªå¥½
    -0.06
    orros
    -0.06
    клаÑģÑģа
    -0.06
    缾
    -0.06
    duc
    -0.06
    POSITIVE LOGITS
    ään
    0.08
     combined
    0.07
    èªĵ
    0.07
    é»ĺ
    0.07
    combined
    0.07
    éĻħ
    0.07
    []}
    0.07
     combinar
    0.07
     جÙĩ
    0.07
    天åĴĮ
    0.07
    Activations Density 0.012%

    No Known Activations