© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 55638
    Prev
    Next
    INDEX
    Explanations

    calculations with parentheses and operators

    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
    eret
    -0.07
    erior
    -0.07
    ahn
    -0.07
    .asc
    -0.07
    enu
    -0.07
    QUIS
    -0.06
    ase
    -0.06
    afil
    -0.06
    quis
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ÙĪØ§Ùħ
    0.08
    æĸ°çĶŁæ´»
    0.07
    icia
    0.07
    velle
    0.07
    æľĿ
    0.06
    emani
    0.06
    isky
    0.06
     Corse
    0.06
    reon
    0.06
    باس
    0.06
    Activations Density 0.013%

    No Known Activations