© 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. 984
    Prev
    Next
    INDEX
    Explanations

    variable declaration or assignment delimiters

    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
    zos
    -0.09
    iato
    -0.08
    egg
    -0.08
    à¹Ĩ
    -0.08
    izion
    -0.08
    tron
    -0.08
    ucci
    -0.08
    Ø©
    -0.08
    isi
    -0.08
    rette
    -0.08
    POSITIVE LOGITS
    ially
    0.07
    åĴĮ她çļĦ
    0.07
    ropping
    0.07
    åĴĮå¤ĸ
    0.07
    empla
    0.06
    ToUpper
    0.06
     behalf
    0.06
    åıĬåħ¶
    0.06
    regor
    0.06
    äºĭäºĨ
    0.06
    Activations Density 0.020%

    No Known Activations