© 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. 38237
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation and symbols

    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
    寻常
    -0.07
    ä¸įåı¯åıĬ
    -0.06
    çĴŀ
    -0.06
    olik
    -0.06
    ishes
    -0.06
    é¢ĸ
    -0.06
    YA
    -0.06
    mdl
    -0.06
    Ñģком
    -0.06
    æľīéĴ±
    -0.06
    POSITIVE LOGITS
    ocache
    0.09
    Indented
    0.08
    åıĪåIJį
    0.08
    abor
    0.08
    DATES
    0.07
    rados
    0.07
    [image
    0.07
     pinterest
    0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹èĵĿåŃĹ
    0.07
    &B
    0.07
    Activations Density 0.024%

    No Known Activations