© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    sorted array

    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
    æĺ¯èĢģ
    -0.07
    oyer
    -0.07
    æĬĸ
    -0.07
    iverse
    -0.07
    éķ¿æĪIJ
    -0.07
    bió
    -0.07
    iento
    -0.06
    ibia
    -0.06
    å¿«èĪ¹
    -0.06
    zd
    -0.06
    POSITIVE LOGITS
    æĩ¿
    0.07
    åIJĮæł·çļĦ
    0.07
    ä»įåľ¨
    0.07
     pula
    0.07
    XC
    0.07
    ë¹µ
    0.07
     stessi
    0.07
    æĽ¦
    0.06
    stones
    0.06
    HP
    0.06
    Activations Density 0.030%

    No Known Activations