© 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. 18887
    Prev
    Next
    INDEX
    Explanations

    turbulent flow or laminar structure

    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
    èİ«åıĬ
    -0.08
    zij
    -0.07
    åĵŃç¬ijä¸įå¾Ĺ
    -0.07
     muta
    -0.07
    åĩĮéľĦ
    -0.07
    æĹıèĩªæ²»
    -0.07
    å¼¥
    -0.07
    çİ®
    -0.07
     metav
    -0.07
    agher
    -0.07
    POSITIVE LOGITS
    ä¸įä¹±
    0.08
    utoff
    0.07
    .flow
    0.07
    à¦Ŀ
    0.07
    åı¯æݧ
    0.07
    çĬ¶æĢģä¸ĭ
    0.07
     flow
    0.07
    Ñıви
    0.06
    -lined
    0.06
     chảy
    0.06
    Activations Density 0.004%

    No Known Activations