© 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. 30630
    Prev
    Next
    INDEX
    Explanations

    ratios

    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
    (es
    -0.07
    igham
    -0.07
    é¦ĸ
    -0.06
    -Cs
    -0.06
    N
    -0.06
    çĭ©
    -0.06
    dem
    -0.06
    (md
    -0.06
    iets
    -0.06
    èĮ¨
    -0.06
    POSITIVE LOGITS
    orsa
    0.08
     ratios
    0.07
    _ratio
    0.07
     Ratio
    0.07
    letic
    0.07
    ansas
    0.07
    orej
    0.07
    ram
    0.07
    leich
    0.07
    æIJº
    0.07
    Activations Density 0.002%

    No Known Activations