© 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. 40081
    Prev
    Next
    INDEX
    Explanations

    photosynthesis structures and processes

    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
    æİĤ
    -0.08
    æ¸Ŀ
    -0.07
     nails
    -0.07
    ãĤ¥
    -0.06
     Zy
    -0.06
     cad
    -0.06
    æĥ¯äºĨ
    -0.06
     habit
    -0.06
    ieux
    -0.06
    Car
    -0.06
    POSITIVE LOGITS
    åħīä¼ı
    0.09
    åħīä¼ıåıijçĶµ
    0.08
    èĨľ
    0.08
    åįĪä¼ij
    0.08
    /photo
    0.08
     ÑģвеÑĤо
    0.08
    羸åŃIJ
    0.08
    çĤİçĤİå¤ıæĹ¥
    0.08
    并ç½ij
    0.08
     pigment
    0.08
    Activations Density 0.030%

    No Known Activations