© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    chemical reaction and oxidation processes

    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
    artner
    -0.08
    _PARAMETERS
    -0.08
    iscal
    -0.08
    resentation
    -0.08
    urus
    -0.07
    èļĮ
    -0.07
    åıĮé±¼
    -0.07
    èĩªéĹŃ
    -0.07
    oge
    -0.07
    ÙĬÙĤ
    -0.07
    POSITIVE LOGITS
    ä¸įæĮī
    0.07
     bitwise
    0.07
    æĺĵçĩĥ
    0.07
    ä¹Łåıªæľī
    0.07
    nikov
    0.07
     propane
    0.07
    itur
    0.07
    สู
    0.07
     outdoors
    0.07
    ÑģÑĤÑĬ
    0.07
    Activations Density 0.003%

    No Known Activations