© 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. 55950
    Prev
    Next
    INDEX
    Explanations

    island names and locations

    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
    lake
    -0.09
     Denver
    -0.08
     panda
    -0.08
    queta
    -0.08
    ãĥijãĤ¯
    -0.07
     Fuller
    -0.07
     ducks
    -0.07
     Gupta
    -0.07
     Panda
    -0.07
    Streamer
    -0.07
    POSITIVE LOGITS
    å²ĽçļĦ
    0.12
    å²Ľ
    0.11
     island
    0.11
    å²Ľä¸Ĭ
    0.11
     sicil
    0.10
     FreeBSD
    0.10
    島ãģ®
    0.10
     Puerto
    0.10
     Sic
    0.10
     Island
    0.10
    Activations Density 0.527%

    No Known Activations