© 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. 40333
    Prev
    Next
    INDEX
    Explanations

    php code and mathematical expressions

    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
    åıĮéĿ¢
    -0.07
    éªģ
    -0.06
    [[
    -0.06
    åħ¸åŀĭ
    -0.06
    mani
    -0.06
    xbf
    -0.06
    oking
    -0.06
    å¹ħ
    -0.06
    åīª
    -0.05
    å¯ĦäºĪ
    -0.05
    POSITIVE LOGITS
    imax
    0.08
    verages
    0.08
    ierte
    0.08
    çļĦåĩĨå¤ĩ
    0.07
    (Have
    0.07
    avail
    0.07
    åĩĨå¤ĩ好çļĦ
    0.07
    گاÙĩ
    0.07
    æĦıæĥ³
    0.07
    iere
    0.07
    Activations Density 0.011%

    No Known Activations