© 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. 45910
    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
    个
    -0.07
    _wrap
    -0.07
    ear
    -0.07
     मà¥Ī
    -0.06
    缮
    -0.06
    enga
    -0.06
    ustom
    -0.06
    wrap
    -0.06
    æѦ
    -0.06
    mers
    -0.06
    POSITIVE LOGITS
    æĿŀ
    0.07
    yli
    0.07
    ongsTo
    0.07
    åºı
    0.07
    missive
    0.07
    гоÑĢиÑĤ
    0.07
    iscrim
    0.07
    нали
    0.07
    oton
    0.07
    ä¸ľè¥¿
    0.07
    Activations Density 0.000%

    No Known Activations