© 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. 17367
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    ath
    -0.08
    #{@
    -0.07
    enschaft
    -0.07
     latter
    -0.07
    èĴĻ
    -0.07
    åIJİèĢħ
    -0.06
    ç¥Ń
    -0.06
    íݸ
    -0.06
    esseract
    -0.06
    èĢ»
    -0.06
    POSITIVE LOGITS
    yron
    0.07
    mlink
    0.07
     Prat
    0.07
    以åįĹ
    0.07
     ssize
    0.06
    .dep
    0.06
    CCI
    0.06
    ä¸Ģ棵
    0.06
    åĮ»å¾·
    0.06
    yz
    0.06
    Activations Density 0.029%

    No Known Activations