© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 31696
    Prev
    Next
    INDEX
    Explanations

    meta tags with name or charset

    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
    çļĦ
    -0.11
    panion
    -0.09
    ìĿĺ
    -0.09
    iht
    -0.09
    ยา
    -0.08
    heits
    -0.08
    ãģ®
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    enius
    -0.08
    zten
    -0.08
    POSITIVE LOGITS
    ness
    0.11
    lessly
    0.09
    itude
    0.08
    ÑģÑĤво
    0.08
    tedir
    0.08
    sw
    0.08
    gether
    0.07
    apult
    0.07
    ãģ¦
    0.07
    issimo
    0.07
    Activations Density 0.006%

    No Known Activations