© 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. 25678
    Prev
    Next
    INDEX
    Explanations

    network connection setup

    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
    Compiler
    -0.07
    .defaultValue
    -0.07
    Ø®Ùħ
    -0.07
    åĪĢåĪĥ
    -0.07
    esar
    -0.06
     EFE
    -0.06
    æīİåħĭ
    -0.06
     intersect
    -0.06
    ä¸įåĩı
    -0.06
    æŃ£è§Ĩ
    -0.06
    POSITIVE LOGITS
     connection
    0.13
    connection
    0.11
    /connection
    0.11
     connections
    0.11
     Connection
    0.11
    è¿ŀæİ¥
    0.10
    åıĮåIJij
    0.10
    Connection
    0.10
    è¿ŀæİ¥çļĦ
    0.10
    .connection
    0.10
    Activations Density 0.336%

    No Known Activations