© 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. 13349
    Prev
    Next
    INDEX
    Explanations

    physical actions

    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
    .getvalue
    -0.07
    bum
    -0.07
    åľ¨è·¯ä¸Ĭ
    -0.07
    구ëĤĺ
    -0.07
    ä¸įåIJĮç¨ĭ度
    -0.07
    缸éļı
    -0.07
    è¶Ĭæĥ³
    -0.07
    è°ĭ
    -0.07
    è·¤
    -0.07
    andar
    -0.06
    POSITIVE LOGITS
    tran
    0.07
    çĦ¶åIJİå°Ĩ
    0.07
    amiliar
    0.07
    äºĨä¸Ĭåİ»
    0.07
    ãģ¤ãĤĤãĤĬ
    0.07
    没æľīä¸Ŀ毫
    0.07
     फिर
    0.07
     painstaking
    0.07
    çĦ¶åIJİæĬĬ
    0.07
    è¿ĺçĶ¨
    0.07
    Activations Density 0.076%

    No Known Activations