© 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. 24344
    Prev
    Next
    INDEX
    Explanations

    variable assignments in expressions

    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
    追åĽŀ
    -0.07
    (percent
    -0.06
    åĽŀæĶ¶
    -0.06
    è¿Ļæł·çļĦä¸Ģ个
    -0.06
     à¸Ńà¸ĩ
    -0.06
    å¤Ń
    -0.06
    Recovered
    -0.06
    umont
    -0.06
    upert
    -0.06
    åľ¨å¹³æŶ
    -0.06
    POSITIVE LOGITS
    Ø°ÙĦ
    0.08
    zcz
    0.07
    haber
    0.07
    çİĭæ°¸
    0.07
    programma
    0.07
    _headers
    0.07
    -<?
    0.07
    -plugins
    0.07
    hound
    0.07
    INAN
    0.07
    Activations Density 0.002%

    No Known Activations