© 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. 21171
    Prev
    Next
    INDEX
    Explanations

    v/w/mol percentages

    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
    ambi
    -0.09
    iei
    -0.09
    orius
    -0.09
     ذا
    -0.08
    ä¸Ń度
    -0.08
    ampu
    -0.07
    亲们
    -0.07
     полнÑĭм
    -0.07
    itie
    -0.07
    ÑħÑĢо
    -0.07
    POSITIVE LOGITS
    çϾåĪĨæ¯Ķ
    0.08
    åįłæ¯Ķ
    0.08
    -wise
    0.08
    å±ĤéĿ¢çļĦ
    0.07
     ratio
    0.07
    ä¸ĬçļĦ
    0.07
     percentage
    0.07
    /
    0.07
     percentages
    0.07
    ½
    0.07
    Activations Density 0.013%

    No Known Activations