© 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. 25699
    Prev
    Next
    INDEX
    Explanations

    virtualization, virtual machines, virtual private

    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
    ¿
    -0.07
    zcz
    -0.07
    ãģ¾ãģĹãģ¦
    -0.07
    ยà¹īำ
    -0.07
    atty
    -0.07
    dart
    -0.07
    åĭĻ
    -0.07
    hift
    -0.07
    eful
    -0.07
    etiš
    -0.07
    POSITIVE LOGITS
    ization
    0.12
    ized
    0.12
    ity
    0.11
    ness
    0.10
    ĮĢ
    0.10
    izable
    0.10
    izing
    0.09
    é«ĺä¸ĵ
    0.09
    isation
    0.09
    ëĤĺë§Ī
    0.09
    Activations Density 0.016%

    No Known Activations