© 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. 63056
    Prev
    Next
    INDEX
    Explanations

    percent tariff

    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
     light
    -0.07
     Light
    -0.07
     parch
    -0.06
     vs
    -0.06
    åŀĤ
    -0.06
     Bright
    -0.06
    2
    -0.06
     del
    -0.06
     versus
    -0.06
    Light
    -0.05
    POSITIVE LOGITS
    weif
    0.09
    urgi
    0.09
    ingleton
    0.09
    BERS
    0.08
    Dragging
    0.08
     Allem
    0.08
     Ilmais
    0.08
    ondi
    0.08
    ledo
    0.08
    ongyang
    0.08
    Activations Density 0.443%

    No Known Activations