© 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. 12718
    Prev
    Next
    INDEX
    Explanations

    bound

    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
    keit
    -0.11
    ussion
    -0.10
    िता
    -0.09
    kenal
    -0.09
    åħĭç¦ı
    -0.09
    ÏĦÏģÏĮ
    -0.09
    entrum
    -0.09
    ï¸İ
    -0.09
    åIJijèį£
    -0.08
    obia
    -0.08
    POSITIVE LOGITS
    edly
    0.13
    ings
    0.10
    ingly
    0.10
    иÑĢов
    0.09
    aries
    0.08
    edList
    0.08
    ers
    0.08
    INGS
    0.07
    a
    0.07
    sWith
    0.07
    Activations Density 0.010%

    No Known Activations