© 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. 31621
    Prev
    Next
    INDEX
    Explanations

    python setup and iostream

    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
    astr
    -0.08
    çļĦæīĢæľīä½ľåĵģ
    -0.07
    ástica
    -0.07
    ætter
    -0.07
     everywhere
    -0.07
    #######
    -0.07
    fic
    -0.07
    вÑĩеÑĢа
    -0.07
     BUFF
    -0.07
    çİĩä½İ
    -0.06
    POSITIVE LOGITS
    åijĹ
    0.07
     Mauro
    0.07
    infeld
    0.06
     #__
    0.06
    activation
    0.06
    欣
    0.06
     ko
    0.06
     jel
    0.06
    erve
    0.06
    umbnail
    0.06
    Activations Density 0.001%

    No Known Activations