© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21648
    Prev
    Next
    INDEX
    Explanations

    specialized terminology

    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
    _DIRECT
    -0.08
    èĮģ
    -0.08
    tura
    -0.08
    ئÛĮ
    -0.07
    DataManager
    -0.07
     ÑĥпÑĢа
    -0.07
     Emergen
    -0.07
    åĺŁåĺŁ
    -0.07
    åĺŁ
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    POSITIVE LOGITS
    è°IJéŁ³
    0.10
    utton
    0.07
     hook
    0.06
     ble
    0.06
    æĪijåIJĹ
    0.06
     pron
    0.06
    oom
    0.06
    åĭ¾
    0.06
    ulum
    0.06
     ter
    0.06
    Activations Density 0.110%

    No Known Activations