© 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. 8691
    Prev
    Next
    INDEX
    Explanations

    swap or switch

    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
    -addons
    -0.09
    InstanceState
    -0.08
     slog
    -0.08
    -addon
    -0.08
    ÑĢони
    -0.08
    eneration
    -0.08
    aign
    -0.08
    ullets
    -0.08
    ÄĻs
    -0.08
    å¦ĤçĥŁ
    -0.07
    POSITIVE LOGITS
     swap
    0.11
     swapping
    0.11
    Swap
    0.10
     swaps
    0.10
    _swap
    0.10
    swap
    0.10
    è°ĥæį¢
    0.10
     Swap
    0.09
    äºĴæį¢
    0.09
    交æį¢
    0.09
    Activations Density 0.004%

    No Known Activations