© 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. 40471
    Prev
    Next
    INDEX
    Explanations

    unknown

    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
     okazji
    -0.08
    Ù°
    -0.08
    SSIP
    -0.07
    aliz
    -0.07
    ddb
    -0.07
    vaard
    -0.07
    ople
    -0.07
    enius
    -0.07
    åĪĽæĸ°ä¸Ńå¿ĥ
    -0.07
    omini
    -0.07
    POSITIVE LOGITS
    ness
    0.08
    ÑģÑı
    0.07
    涯
    0.07
    à¸ķัว
    0.07
     quantity
    0.07
    éĩı
    0.06
    åĴĮéĩįçĤ¹
    0.06
    åĴĮå¸ĮæľĽ
    0.06
    羣å¿ĥçļĦ
    0.06
    inste
    0.06
    Activations Density 0.005%

    No Known Activations