© 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. 28744
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code snippets

    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
    åĨĴ
    -0.09
    enu
    -0.07
    笳
    -0.07
    empel
    -0.06
    anches
    -0.06
    ê°
    -0.06
    Ùİاب
    -0.06
     eup
    -0.06
    urang
    -0.06
    orne
    -0.06
    POSITIVE LOGITS
     shouldn
    0.07
    ä¸Ģå¤ķ
    0.07
    ritable
    0.07
    utorial
    0.07
    æŀĦ
    0.07
    å»
    0.07
    apres
    0.07
    itz
    0.06
    äºĮçŃī
    0.06
    رسÛĮ
    0.06
    Activations Density 0.065%

    No Known Activations