© 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. 32145
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions

    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
    -0.06
    liers
    -0.06
    寸
    -0.06
     pinpoint
    -0.06
    /
    -0.06
    çľ¼çļĦ
    -0.06
     surrounding
    -0.06
    åīįéĿ¢çļĦ
    -0.06
    or
    -0.05
    -
    -0.05
    POSITIVE LOGITS
    alu
    0.09
    бÑĸ
    0.09
    以åıĬåIJĦç§į
    0.09
    åħĥç¥ŀ
    0.09
     Valor
    0.08
    inheiten
    0.08
    ourg
    0.08
    alars
    0.08
     nameLabel
    0.08
    йн
    0.08
    Activations Density 0.002%

    No Known Activations