© 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. 10794
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    ulier
    -0.08
    alde
    -0.08
    ivery
    -0.08
    atter
    -0.08
    _war
    -0.07
    lections
    -0.07
    idação
    -0.07
    äter
    -0.07
    å¿ĥäºĭ
    -0.07
    ido
    -0.07
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.09
     nor
    0.07
    roll
    0.07
    fa
    0.07
     Nor
    0.07
    ÏĢÎŃ
    0.07
     einst
    0.07
    èĢĮæĺ¯åĽłä¸º
    0.07
    £
    0.06
    èĢĮæĺ¯è¦ģ
    0.06
    Activations Density 0.070%

    No Known Activations