© 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. 49667
    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
     invers
    -0.08
    adir
    -0.07
    пÑĮ
    -0.07
    åıĪæĿ¥äºĨ
    -0.07
    .charCodeAt
    -0.07
    åIJİæĦŁ
    -0.07
    ucher
    -0.07
    rire
    -0.06
    _IB
    -0.06
    asd
    -0.06
    POSITIVE LOGITS
    berger
    0.07
    лик
    0.07
    -export
    0.07
    å¿«åĪ°
    0.06
     Doming
    0.06
    System
    0.06
    _SORT
    0.06
    otka
    0.06
    aight
    0.06
     knowingly
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.