© 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. 33320
    Prev
    Next
    INDEX
    Explanations

    comparison or reliance

    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
    estan
    -0.08
     Ramos
    -0.07
    /apis
    -0.07
    lfw
    -0.07
    anine
    -0.07
    çŃ
    -0.07
    æĺİåªļ
    -0.07
    WAN
    -0.07
    ми
    -0.07
    ரிய
    -0.07
    POSITIVE LOGITS
    åĢŁåĬ©
    0.11
     reliance
    0.09
    ä¾Ŀèµĸ
    0.09
     relying
    0.08
     mengandalkan
    0.08
    ä¾Ŀæīĺ
    0.08
     rely
    0.08
    åĢļ
    0.08
    éĿłçĿĢ
    0.08
    ä¾Ŀèµĸäºİ
    0.07
    Activations Density 0.625%

    No Known Activations