© 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. 40808
    Prev
    Next
    INDEX
    Explanations

    mathematical summation of numbers

    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
    ugu
    -0.08
    geld
    -0.07
    uit
    -0.07
    оди
    -0.07
    åĽ½å®¶ä¸Ģ级
    -0.07
    (previous
    -0.07
    izon
    -0.07
    odo
    -0.06
    agne
    -0.06
    íĻ©
    -0.06
    POSITIVE LOGITS
    inkl
    0.08
     Mitar
    0.07
    reen
    0.07
    åŃľ
    0.07
    евиÑĩ
    0.07
    åIJ«
    0.07
    ADAS
    0.07
     Nuc
    0.06
    rez
    0.06
    áĥIJáĥ®
    0.06
    Activations Density 0.011%

    No Known Activations