© 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. 43424
    Prev
    Next
    INDEX
    Explanations

    string manipulation and case conversion

    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
    çī¹æĸ¯
    -0.07
    cratch
    -0.07
    czyn
    -0.06
    rien
    -0.06
     ad
    -0.06
     eft
    -0.06
    جا
    -0.06
    che
    -0.06
    avo
    -0.06
    exus
    -0.06
    POSITIVE LOGITS
    èļĮ
    0.07
    rott
    0.07
    oseb
    0.07
    orn
    0.07
     Attr
    0.07
    orsi
    0.07
    å¾Īå¤ļäºĭæĥħ
    0.07
    åıijçİ°èĩªå·±çļĦ
    0.07
    èĴĻ
    0.07
    osat
    0.07
    Activations Density 0.001%

    No Known Activations