© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20516
    Prev
    Next
    INDEX
    Explanations

    function arguments or types

    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
    /gtest
    -0.07
    ÙĴرÙIJ
    -0.07
    arness
    -0.07
    arkin
    -0.07
    {}_
    -0.07
    ERG
    -0.07
    æķıæĦŁåº¦
    -0.06
    heen
    -0.06
    èĿ¶
    -0.06
    Prop
    -0.06
    POSITIVE LOGITS
    okok
    0.07
     Literal
    0.07
    chwitz
    0.07
    lobals
    0.07
    roke
    0.07
    osan
    0.06
    åĮĸåѦçī©è´¨
    0.06
    æĢİæł·åģļ
    0.06
    äºĶåij³
    0.06
    _ASM
    0.06
    Activations Density 0.001%

    No Known Activations