© 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. 44968
    Prev
    Next
    INDEX
    Explanations

    The business entrepreneur thing

    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
     vest
    -0.06
     inv
    -0.06
    æĭ£
    -0.06
    åĽº
    -0.06
    ä¸ĢæŃ¥
    -0.06
    ä¸Ĭ人
    -0.06
    acting
    -0.06
    ait
    -0.06
    .wordpress
    -0.06
    ç®Ģ书
    -0.06
    POSITIVE LOGITS
    ossal
    0.09
    給èĩªå·±
    0.08
    FilePath
    0.08
    alan
    0.08
    ç»Ħç»ĩåѦçĶŁ
    0.07
    abora
    0.07
    èį·
    0.07
    aal
    0.07
    lake
    0.07
     carga
    0.07
    Activations Density 0.001%

    No Known Activations