© 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. 62870
    Prev
    Next
    INDEX
    Explanations

    a number of

    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
    istring
    -0.08
    èĩªæľī
    -0.07
    edb
    -0.07
    ãĤ¡
    -0.07
    è¨Ģéģĵ
    -0.07
    alha
    -0.07
    天æĺİ
    -0.07
    alina
    -0.07
    丰å¯Įå¤ļ彩çļĦ
    -0.07
    ieuse
    -0.07
    POSITIVE LOGITS
    lasan
    0.07
    argas
    0.07
    åİŁæĸĩåĩºå¤Ħ
    0.07
    è¿Ļæł·åģļ
    0.07
    True
    0.07
     True
    0.07
    è¿Ļè¯Ŀ
    0.06
    imes
    0.06
    ´
    0.06
    ×Ĺ×ķת
    0.06
    Activations Density 0.099%

    No Known Activations