© 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. 18442
    Prev
    Next
    INDEX
    Explanations

    first- class, -on, -the

    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
    unga
    -0.07
    ullet
    -0.06
    aliz
    -0.06
    groupId
    -0.06
    stat
    -0.06
     anon
    -0.06
    aeda
    -0.06
     VERSION
    -0.06
    omba
    -0.06
    Untitled
    -0.06
    POSITIVE LOGITS
    erc
    0.07
    ä¸ĬæľĪ
    0.07
    antica
    0.07
    ught
    0.07
    acol
    0.07
    Ø´ÛĮ
    0.07
    erty
    0.07
    åħ¨ç¾İ
    0.07
    ossal
    0.07
    该项
    0.07
    Activations Density 0.016%

    No Known Activations