© 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. 15538
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical terms

    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
    iru
    -0.08
    ÙĨب
    -0.07
     mitra
    -0.07
    enni
    -0.07
    enti
    -0.07
    asco
    -0.06
    rem
    -0.06
    çģ¿çģ¿
    -0.06
    _globals
    -0.06
    äºļçī¹
    -0.06
    POSITIVE LOGITS
    fro
    0.08
    KHR
    0.07
    gue
    0.07
    inary
    0.07
    DIM
    0.07
    çĻ¾éĩĮ
    0.07
    ä¸ĢæĿ¡é¾Ļ
    0.07
    à®°à®ļ
    0.07
    fade
    0.07
     BPK
    0.07
    Activations Density 0.002%

    No Known Activations