© 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. 28354
    Prev
    Next
    INDEX
    Explanations

    proportion / ratio

    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
    InMillis
    -0.08
    alue
    -0.07
    иÑħ
    -0.07
    pris
    -0.07
    quer
    -0.07
    æĬĺ
    -0.07
    Ùĩب
    -0.06
    ppers
    -0.06
    çĨł
    -0.06
    Origin
    -0.06
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.09
    æ¯Ķä¾ĭçļĦ
    0.09
     proportion
    0.08
    icen
    0.08
    æĢ»æķ°
    0.08
    æĢ»æķ°çļĦ
    0.08
     minority
    0.07
    为主çļĦ
    0.07
     ratio
    0.07
    æĬļ
    0.07
    Activations Density 0.001%

    No Known Activations