© 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. 64622
    Prev
    Next
    INDEX
    Explanations

    equation parts

    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
    OTAL
    -0.08
    ection
    -0.08
    ingi
    -0.08
    StackTrace
    -0.07
    åĴĮèµĦæºIJ
    -0.07
    :value
    -0.07
    OTOR
    -0.07
    ENUM
    -0.07
    Addr
    -0.07
    į
    -0.07
    POSITIVE LOGITS
    ason
    0.07
    angles
    0.07
    çĿĢä¸ĢèĤ¡
    0.06
    raje
    0.06
    ights
    0.06
    stand
    0.06
    elves
    0.06
    éĿĴ年人
    0.06
     Schmidt
    0.06
    erge
    0.06
    Activations Density 0.003%

    No Known Activations