© 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. 8409
    Prev
    Next
    INDEX
    Explanations

    focal length of lenses

    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
    æłĩ段
    -0.07
    angk
    -0.07
    imb
    -0.07
    æĴŃ
    -0.07
    åĵģåij³
    -0.06
    lecht
    -0.06
    æµ·åŁŁ
    -0.06
     Simone
    -0.06
    ëĿ½
    -0.06
    ros
    -0.06
    POSITIVE LOGITS
    çĦ¦è·Ŀ
    0.12
    æĪIJåĥı
    0.10
    çĦ¦
    0.10
    éĢıéķľ
    0.10
    çĦ¦çĤ¹
    0.09
    éķľçīĩ
    0.09
     optics
    0.09
    ãĥ¬ãĥ³ãĤº
    0.09
     Imaging
    0.08
     lenses
    0.08
    Activations Density 0.003%

    No Known Activations