© 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. 40138
    Prev
    Next
    INDEX
    Explanations

    fluid flow and drainage systems

    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
    交çĶµ
    -0.08
    åĪĢåĪĥ
    -0.07
    çĥŃå¤ĦçIJĨ
    -0.07
     orthogonal
    -0.07
    éĺ»çĩĥ
    -0.07
    çĥŃ轧
    -0.07
    çŃĭ骨
    -0.07
     Scaffold
    -0.07
     intellectual
    -0.07
    驾é©Ń
    -0.07
    POSITIVE LOGITS
    è¿ŀéĢļ
    0.13
    è¿ŀæİ¥
    0.11
    connections
    0.10
    è¿ŀæİ¥çļĦ
    0.10
    connected
    0.10
     ìĹ°ê²°
    0.10
    管路
    0.10
     connected
    0.10
     connections
    0.10
    容积
    0.10
    Activations Density 0.184%

    No Known Activations