© 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. 60669
    Prev
    Next
    INDEX
    Explanations

    city names and area suffixes

    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
    ought
    -0.07
    æµ¦ä¸ľæĸ°åĮº
    -0.07
    ä¹ĭ忧
    -0.07
    æł¹æľ¬å°±ä¸į
    -0.06
    cke
    -0.06
    upas
    -0.06
    ä¸Ģåİ»
    -0.06
    亡
    -0.06
    urv
    -0.06
    lod
    -0.06
    POSITIVE LOGITS
    åıĬåij¨è¾¹
    0.11
    æľ¬åľ°çļĦ
    0.10
    æľ¬åľ°
    0.09
    Äı
    0.09
    adle
    0.08
    locals
    0.08
    abouts
    0.08
    _plugins
    0.08
    COOKIE
    0.08
    pressa
    0.08
    Activations Density 1.199%

    No Known Activations