© 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. 21953
    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
    кок
    -0.08
    å®ŀä¹łæĬ¥åijĬ
    -0.06
     Virgin
    -0.06
    <tag
    -0.06
    à¹īา
    -0.06
    heits
    -0.06
     apt
    -0.06
    ãĥĬãĥĥãĥĹ
    -0.06
    loat
    -0.06
    lys
    -0.06
    POSITIVE LOGITS
    寸
    0.07
    ien
    0.07
    ardy
    0.07
    éķ¿ä¹IJ
    0.07
    enumerate
    0.06
    ardini
    0.06
    çIJ³å¨ľ
    0.06
    encil
    0.06
    _specs
    0.06
    icator
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.