© 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. 45998
    Prev
    Next
    INDEX
    Explanations

    light sources and lasers

    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
    alien
    -0.08
    izas
    -0.08
     Tél
    -0.07
    _To
    -0.07
    æ²īæµ®
    -0.07
    æĥĬå¿ĥ
    -0.07
    æİ¥åIJ¬
    -0.07
    udio
    -0.07
     подлежаÑĤ
    -0.07
    åıĺçİ°
    -0.07
    POSITIVE LOGITS
    æºIJ
    0.14
     sources
    0.14
     source
    0.14
    æºIJçļĦ
    0.13
    source
    0.13
     Source
    0.12
    åħīæºIJ
    0.12
    Source
    0.12
     Sources
    0.12
    ä¾ĨæºIJ
    0.12
    Activations Density 0.060%

    No Known Activations