© 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. 18387
    Prev
    Next
    INDEX
    Explanations

    membrane proteins

    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
    没æľīåĩºçİ°
    -0.07
    æĶ¯çº¿
    -0.07
    orce
    -0.07
    åŃķèĤ²
    -0.07
    ìľ
    -0.07
    弥漫çĿĢ
    -0.07
    室åĨħ空æ°Ķ
    -0.07
    /sources
    -0.07
    TextStyle
    -0.06
    å¦ĤæĦı
    -0.06
    POSITIVE LOGITS
     functional
    0.10
    /function
    0.09
    çļĦåĬŁèĥ½
    0.08
    åĬŁèĥ½æĢ§
    0.08
    licated
    0.08
    åĬŁèĥ½çļĦ
    0.08
     proteins
    0.08
    functional
    0.08
    åĬŁèĥ½
    0.08
    Functional
    0.08
    Activations Density 0.132%

    No Known Activations