© 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. 45452
    Prev
    Next
    INDEX
    Explanations

    code addition

    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
    ondre
    -0.08
    ór
    -0.07
    åĬ
    -0.06
    æĸĻçļĦ
    -0.06
    cy
    -0.06
    票
    -0.06
    utat
    -0.06
    åIJijåħ¶
    -0.06
    grad
    -0.06
    Grad
    -0.06
    POSITIVE LOGITS
    bens
    0.08
    æĹłèĻij
    0.07
    thon
    0.07
    acqu
    0.07
     fiz
    0.07
    asilan
    0.07
    fiz
    0.07
    NewProp
    0.07
    land
    0.07
    mitt
    0.07
    Activations Density 0.054%

    No Known Activations