© 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. 41694
    Prev
    Next
    INDEX
    Explanations

    external links

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    åľ¨æīĢ
    -0.08
    èı
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
    åįģä¸Ģç«ł
    -0.07
    TL
    -0.07
    该楼å±Ĥçĸijä¼¼è¿Ŀè§Ħå·²è¢«ç³»ç»ŁæĬĺåıł
    -0.07
    _DESCRIPTOR
    -0.07
    åĽŀçŃĶéĩı
    -0.07
    å±±ä¸Ń
    -0.07
    POSITIVE LOGITS
    æĿĥå¨ģ
    0.08
    sources
    0.08
     sources
    0.07
    APPER
    0.07
    æĿĥå¨ģçļĦ
    0.07
    otts
    0.07
    https
    0.07
    æ¬Ĭå¨ģ
    0.07
    theses
    0.07
    IONS
    0.07
    Activations Density 0.045%

    No Known Activations