© 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. 49973
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    atom
    -0.09
    zel
    -0.07
    amai
    -0.07
    ë§ĪìŀIJ
    -0.07
    .atom
    -0.07
    sher
    -0.07
    issan
    -0.07
    phant
    -0.07
    çĥĤ
    -0.07
    combe
    -0.07
    POSITIVE LOGITS
    undet
    0.08
    à¦ľà¦¨
    0.07
    æĬĬè¿Ļ
    0.07
    é£İå°ĺ
    0.07
    nul
    0.06
    è¿Ľè¡Įå®¡æł¸
    0.06
    Ú©Ø´
    0.06
    æľīåĬł
    0.06
    uto
    0.06
    itulo
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.