© 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. 47080
    Prev
    Next
    INDEX
    Explanations

    groups and their properties

    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
    etak
    -0.08
    çĪ·
    -0.07
    lot
    -0.07
    åħ¶æīĢ
    -0.07
    ert
    -0.07
    ASK
    -0.07
    et
    -0.07
    ابة
    -0.07
    ugi
    -0.07
    rzy
    -0.07
    POSITIVE LOGITS
    壮大çļĦ
    0.07
     Sprecher
    0.07
    олÑĮ
    0.07
    lander
    0.07
    оÑĢо
    0.07
    tui
    0.07
    airie
    0.07
    gó
    0.07
    enant
    0.07
    áĥĿáĥij
    0.06
    Activations Density 0.002%

    No Known Activations