© 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. 28350
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    zio
    -0.07
    URNS
    -0.07
    isé
    -0.07
    irk
    -0.07
    ables
    -0.07
    erties
    -0.07
    ses
    -0.06
    voke
    -0.06
    ional
    -0.06
    ions
    -0.06
    POSITIVE LOGITS
    acin
    0.07
    edin
    0.07
    ód
    0.07
     ÙħØŃÙĦ
    0.06
    å²ļ
    0.06
    æºIJåľ°
    0.06
    èv
    0.06
    umento
    0.06
    allon
    0.06
    ëŀĮ
    0.06
    Activations Density 0.059%

    No Known Activations