© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4833
    Prev
    Next
    INDEX
    Explanations

    URL, copyright, license, research, development

    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
    Negative Logits
    rade
    -0.08
    éħ
    -0.07
    incy
    -0.07
    é£
    -0.07
    [sizeof
    -0.06
    itect
    -0.06
    çµ²
    -0.06
    诧å¼Ĥ
    -0.06
     raw
    -0.06
    çĽ
    -0.06
    POSITIVE LOGITS
     Ñĥп
    0.09
    GRE
    0.08
    è¯Ħ
    0.08
     autogenerated
    0.07
    佬
    0.07
    æŃ£ç»ı
    0.07
    è¾ħ导
    0.07
     PROP
    0.07
    بار
    0.07
    æ³ķæ²»
    0.07
    Activations Density 0.001%

    No Known Activations