© 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. 7661
    Prev
    Next
    INDEX
    Explanations

    line breaks

    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
     Uncategorized
    -0.08
    kow
    -0.08
    ledo
    -0.08
    ugas
    -0.07
    اÛĮد
    -0.07
    baum
    -0.07
    å±ķå¼Ģåħ¨éĥ¨
    -0.07
    urd
    -0.07
    odoro
    -0.07
    å¦ĤæľŁ
    -0.07
    POSITIVE LOGITS
    .ua
    0.08
    dig
    0.07
    dish
    0.07
    ä¿¡
    0.07
    Ī
    0.07
    ÑĪенÑĮ
    0.06
    ÉĻs
    0.06
     dig
    0.06
    说罢
    0.06
    мелÑĮ
    0.06
    Activations Density 0.043%

    No Known Activations