© 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. 21720
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    onato
    -0.08
    تÙħ
    -0.07
    ank
    -0.07
    Ø©
    -0.07
    меÑĢ
    -0.07
    angnya
    -0.07
    arque
    -0.07
    ارة
    -0.06
    رة
    -0.06
     <<-
    -0.06
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.12
    ª
    0.08
     tiên
    0.08
    -ever
    0.07
    STYPE
    0.07
    itarian
    0.07
    °
    0.07
    зви
    0.06
    罪éŃģ
    0.06
    ystone
    0.06
    Activations Density 0.022%

    No Known Activations