© 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. 50165
    Prev
    Next
    INDEX
    Explanations

    travis-ci.org

    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
    oura
    -0.10
    èİħ
    -0.08
    adat
    -0.07
    esy
    -0.07
    onet
    -0.07
    coon
    -0.07
    YLON
    -0.07
    à¦¿à¦ľ
    -0.07
    õt
    -0.07
    endl
    -0.07
    POSITIVE LOGITS
    Ĭ
    0.07
     Hover
    0.07
    _subs
    0.06
    åĬĽ
    0.06
    agh
    0.06
    agne
    0.06
     stripslashes
    0.06
    lık
    0.06
    ëĭĪ
    0.06
    avid
    0.06
    Activations Density 0.061%

    No Known Activations