© 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. 26270
    Prev
    Next
    INDEX
    Explanations

    check for emptiness or null

    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
    åı¯èĥ½å°±æĺ¯
    -0.08
    falls
    -0.08
    ogos
    -0.07
    iaz
    -0.07
    ignite
    -0.07
    ights
    -0.07
    å°±æĺ¯æĪij
    -0.07
    çŁ¥è¯ĨåĴĮæĬĢèĥ½
    -0.07
    åħ¶å®ŀå°±æĺ¯
    -0.07
    à¸ģัà¸Ļà¹Ħà¸Ľ
    -0.06
    POSITIVE LOGITS
     &&
    0.09
    ä¸Ķ
    0.09
    并ä¸Ķ
    0.08
    ä¸Ķæľī
    0.08
     Rowe
    0.08
    ä¸İåIJ¦
    0.08
    ä¸Ķåľ¨
    0.07
    就说æĺİ
    0.07
    icka
    0.07
    &&
    0.07
    Activations Density 0.092%

    No Known Activations