© 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. 24430
    Prev
    Next
    INDEX
    Explanations

    applying rules

    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
    plevel
    -0.09
    ILON
    -0.09
    sce
    -0.08
    iels
    -0.08
    iture
    -0.08
    entifier
    -0.07
    NotAllowed
    -0.07
    ekut
    -0.07
    redients
    -0.07
    redicate
    -0.07
    POSITIVE LOGITS
    fully
    0.11
    zinho
    0.10
    lessness
    0.09
     Äijắn
    0.09
    less
    0.08
    lessly
    0.08
    åı¯å¾ª
    0.08
    ful
    0.08
    witz
    0.07
    ÙħÙĨد
    0.07
    Activations Density 0.029%

    No Known Activations