© 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. 1826
    Prev
    Next
    INDEX
    Explanations

    attributes and programming terms

    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
    æĢĿæĺİ
    -0.08
    æ±Ģ
    -0.08
    ippo
    -0.07
     saz
    -0.07
    umul
    -0.07
    ottom
    -0.07
    笳
    -0.07
    ØŃاد
    -0.07
    swer
    -0.07
     cá»ijt
    -0.07
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.07
     Soph
    0.07
    éĨ
    0.07
    WebpackPlugin
    0.06
    ces
    0.06
    efeld
    0.06
    æĹłæķĮ
    0.06
    æľ«
    0.06
    åĨī
    0.06
    éĻįèĩ³
    0.06
    Activations Density 0.250%

    No Known Activations