© 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. 62340
    Prev
    Next
    INDEX
    Explanations

    start and end date

    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
    æľªå©ļ
    -0.07
    agd
    -0.07
    adge
    -0.07
    .Assign
    -0.07
    缨
    -0.07
    agan
    -0.07
     Knock
    -0.07
    ette
    -0.07
    åģı
    -0.06
    å¦Ĩ
    -0.06
    POSITIVE LOGITS
     bounding
    0.14
     enclosing
    0.14
     boundaries
    0.14
    åĽ´
    0.13
    _boundary
    0.13
     bounds
    0.13
    åĮħåĽ´
    0.13
    èµ·æŃ¢
    0.12
     boundary
    0.12
    åĮºéĹ´
    0.12
    Activations Density 0.189%

    No Known Activations