© 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. 51094
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    .scala
    -0.08
     mana
    -0.08
    $__
    -0.07
    accio
    -0.07
    aida
    -0.07
    éģĩäºĭ
    -0.07
    æĸ¹æīį
    -0.07
    æī¬éķ¿
    -0.07
     Bruder
    -0.07
    ัà¸Ī
    -0.07
    POSITIVE LOGITS
    lear
    0.08
    æĿİå°ı
    0.07
    hn
    0.07
    ingo
    0.07
    à¸ļุ
    0.07
    amani
    0.07
    大ä¸Ģ
    0.06
    jab
    0.06
    ungsk
    0.06
    µ
    0.06
    Activations Density 0.041%

    No Known Activations