© 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. 25976
    Prev
    Next
    INDEX
    Explanations

    github links

    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
    uggy
    -0.09
    iby
    -0.09
    eneg
    -0.09
    teh
    -0.08
    ubl
    -0.08
    á»ĭn
    -0.08
    дне
    -0.08
    ency
    -0.08
    sei
    -0.08
    rena
    -0.08
    POSITIVE LOGITS
    .com
    0.07
    itarian
    0.06
    amakan
    0.06
     Navarra
    0.06
    клон
    0.05
    ãģ£ãģ¨
    0.05
     ramach
    0.05
    á»Ĺi
    0.05
    µ
    0.05
    vious
    0.05
    Activations Density 0.041%

    No Known Activations