© 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. 62185
    Prev
    Next
    INDEX
    Explanations

    Öther names

    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
    igli
    -0.07
    鸾
    -0.07
    OTOS
    -0.07
    iette
    -0.07
    oliv
    -0.07
    kev
    -0.07
    ТÐĴ
    -0.07
    é¾Ļæ±Ł
    -0.06
    Ùģر
    -0.06
    adak
    -0.06
    POSITIVE LOGITS
    åīĶéĢı
    0.07
    æĭł
    0.07
    缺失
    0.07
    天ä¸ĭ
    0.07
    ays
    0.07
    请èģĶç³»æĪij们åĪłéĻ¤
    0.07
    对ä¸Ĭè¿°
    0.06
    åIJĮä¸Ĭ
    0.06
    zier
    0.06
     prerequisites
    0.06
    Activations Density 0.003%

    No Known Activations