© 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. 63618
    Prev
    Next
    INDEX
    Explanations

    tree and its context

    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
    ities
    -0.09
    íĴĪìĿĦ
    -0.08
    uzzi
    -0.08
    ر
    -0.08
    ï¸İ
    -0.08
    .au
    -0.08
    ìĶ©
    -0.08
    fieldset
    -0.08
    umente
    -0.08
    ëĭ¥
    -0.08
    POSITIVE LOGITS
    Ø©
    0.09
    hood
    0.08
    ocken
    0.08
    ellers
    0.08
    eller
    0.07
    äch
    0.07
    -building
    0.07
    esis
    0.07
    oidal
    0.07
    oretical
    0.07
    Activations Density 0.026%

    No Known Activations