© 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. 15691
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    zer
    -0.09
    æݧ
    -0.08
    awa
    -0.08
    ilai
    -0.06
    å¯Ħ宿
    -0.06
    æ³ĽæĮĩ
    -0.06
    溪
    -0.06
    åĿĹ
    -0.06
    .jquery
    -0.06
    ç¿ł
    -0.06
    POSITIVE LOGITS
    argas
    0.08
    ObjectContext
    0.08
    é«ĺæĺİ
    0.08
    _CURSOR
    0.07
    enen
    0.07
    ãĤĬè¿Ķ
    0.07
    æĿ·
    0.07
    BackingField
    0.07
    prs
    0.07
    ¿IJ
    0.07
    Activations Density 0.001%

    No Known Activations