© 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. 17705
    Prev
    Next
    INDEX
    Explanations

    link to download or license

    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
    schild
    -0.08
    erbe
    -0.07
    asionally
    -0.07
    ayet
    -0.07
    θÏį
    -0.06
    ascus
    -0.06
    æķħèĢĮ
    -0.06
    ç¿
    -0.06
    shaw
    -0.06
    cesa
    -0.06
    POSITIVE LOGITS
     total
    0.09
    oretical
    0.09
     expected
    0.08
     posible
    0.08
     maximum
    0.08
     possible
    0.08
    æĢ»
    0.08
    æľĢ大
    0.08
     required
    0.07
    主ãģª
    0.07
    Activations Density 0.030%

    No Known Activations