© 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. 45627
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structures

    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
    azin
    -0.07
    åĩºä¸Ģ个
    -0.06
    anagan
    -0.06
     декла
    -0.06
    鸣è¯Ń
    -0.06
    对äºİä¸Ģ个
    -0.06
    å±ij
    -0.06
    боÑİ
    -0.06
    ä¿Ŀéļľå·¥ä½ľ
    -0.06
    .createElement
    -0.06
    POSITIVE LOGITS
    soever
    0.08
    ulum
    0.08
    è¿Ļ项
    0.08
    lessly
    0.08
    semb
    0.08
    å§ĭèĩ³ç»Ī
    0.08
    åĩĨ
    0.08
    !]
    0.08
    ¸
    0.07
     Sust
    0.07
    Activations Density 0.002%

    No Known Activations