© 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. 18140
    Prev
    Next
    INDEX
    Explanations

    code syntax like boolean

    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
    èµĮ
    -0.07
    éĿłçĿĢ
    -0.07
    主è¦ģåĪĨ为
    -0.06
     diagnos
    -0.06
    º
    -0.06
    éĻĦè¿ijæľī
    -0.06
    cel
    -0.06
     exc
    -0.06
    .exists
    -0.06
    æĴijçĿĢ
    -0.06
    POSITIVE LOGITS
    alsy
    0.08
    ully
    0.08
    ì·¨
    0.08
     Ente
    0.08
    Falsy
    0.08
    kena
    0.08
    æĢĿæºIJ
    0.08
     конÑģ
    0.07
    ãĤ¹ãĤŃ
    0.07
    кÑĥлÑıÑĢ
    0.07
    Activations Density 0.002%

    No Known Activations