© 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. 14061
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
    ajer
    -0.09
    ummer
    -0.08
     spectrum
    -0.08
    ubu
    -0.08
     Spectrum
    -0.07
    ippo
    -0.07
     Fargo
    -0.07
    çݯå¢ĥè´¨éĩı
    -0.07
    jek
    -0.07
     twe
    -0.07
    POSITIVE LOGITS
    ATEN
    0.08
    _digits
    0.07
    æİ¥åIJ¬
    0.07
    ÙĤاÙĤ
    0.07
     digit
    0.07
    缴åĪ°
    0.07
    fine
    0.07
    opan
    0.07
    à¸Łà¸¹
    0.07
     Gutenberg
    0.07
    Activations Density 0.003%

    No Known Activations