© 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. 19091
    Prev
    Next
    INDEX
    Explanations

    leader or official title

    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
    æľ¬äºĭ
    -0.08
    以åħįéĢłæĪIJ
    -0.08
    perse
    -0.08
    veda
    -0.07
    åĪĽå»ºäºİ
    -0.07
    åı«åģļ
    -0.07
    åIJĦ级åħļå§Ķ
    -0.07
    arau
    -0.07
    illas
    -0.07
     seng
    -0.07
    POSITIVE LOGITS
     duties
    0.11
    ãĤĴåĭĻ
    0.10
     coveted
    0.09
    éĩįä»»
    0.09
    åħ¼ä»»
    0.08
     responsibilities
    0.08
    æİ¥æĽ¿
    0.08
     youngest
    0.08
    çŃīéĩįè¦ģ
    0.08
     interim
    0.07
    Activations Density 0.556%

    No Known Activations