© 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. 64490
    Prev
    Next
    INDEX
    Explanations

    can load or activate

    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
    å°ļ
    -0.07
    Fi
    -0.07
    ires
    -0.07
    çijľ
    -0.07
    ov
    -0.07
     ente
    -0.06
    äºĨæī¿
    -0.06
    iar
    -0.06
    ix
    -0.06
    ente
    -0.06
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.08
    º¼
    0.08
    eway
    0.07
     пÑĢопи
    0.07
    第äºĮéĥ¨åĪĨ
    0.07
    åIJİéĿ¢çļĦ
    0.07
    èIJ½æĹ¥
    0.07
     séd
    0.07
    第äºĮéĺ¶æ®µ
    0.07
    å¼ıä¸Ń
    0.07
    Activations Density 0.010%

    No Known Activations