© 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. 19889
    Prev
    Next
    INDEX
    Explanations

    numbers, ratio, percent

    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
    ieb
    -0.09
    ievo
    -0.08
    à´ªàµįà´ªàµĨ
    -0.08
    oces
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    okka
    -0.08
    åıĮ羸
    -0.08
     Ñįкзо
    -0.08
    é»ĺ认æİĴåºı
    -0.08
    ثة
    -0.08
    POSITIVE LOGITS
    ifiable
    0.07
    æģ©çĪ±
    0.06
    oh
    0.06
     numbers
    0.06
    æķ°
    0.06
     angka
    0.06
     ratio
    0.06
     percent
    0.06
     Numbers
    0.06
    numbers
    0.06
    Activations Density 0.001%

    No Known Activations