© 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. 4053
    Prev
    Next
    INDEX
    Explanations

    secant and theta

    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
     ("-
    -0.08
    åIJ¬åĻ¨
    -0.07
    çĹĴ
    -0.07
    念
    -0.07
    ¹Ħ
    -0.07
    rike
    -0.07
    reno
    -0.07
    ergen
    -0.06
    èĮĹ
    -0.06
    æľ¬åįķä½į
    -0.06
    POSITIVE LOGITS
     séc
    0.08
     모ìĬµ
    0.07
    AspectRatio
    0.07
    ØŃÙĥ
    0.07
    [[
    0.07
    æķ¦
    0.07
    çĻ½éľ²
    0.07
    æĮĩæŃ£
    0.07
    zub
    0.06
    วี
    0.06
    Activations Density 0.002%

    No Known Activations