© 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. 23580
    Prev
    Next
    INDEX
    Explanations

    complex form

    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
    esis
    -0.07
    ñez
    -0.07
    ürf
    -0.07
    çıĬ
    -0.06
    Scr
    -0.06
    ØŃص
    -0.06
    ابة
    -0.06
    ucer
    -0.06
    erii
    -0.06
    rau
    -0.06
    POSITIVE LOGITS
    ista
    0.07
    tools
    0.07
    okin
    0.07
    -signed
    0.07
    stuff
    0.07
    iste
    0.07
    spell
    0.07
    ÑģÑĤок
    0.07
    ials
    0.07
    ilty
    0.07
    Activations Density 0.003%

    No Known Activations