© 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. 62993
    Prev
    Next
    INDEX
    Explanations

    financial amounts in dollars

    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
    建设æĬķèµĦ
    -0.07
    inger
    -0.07
    _HINT
    -0.07
    rick
    -0.07
    _utils
    -0.07
    å¤ļè§ģ
    -0.07
    asian
    -0.07
    趣
    -0.06
    ä¹ĭçĪ¶
    -0.06
    åŃ¦ä¹łçĶŁæ´»
    -0.06
    POSITIVE LOGITS
    isd
    0.08
    èĦ
    0.07
    orate
    0.07
    äºijéľĦ
    0.06
    欣
    0.06
    æį²
    0.06
    èĴIJ
    0.06
    ¤íŀ
    0.06
    æĹĭ
    0.06
    XHR
    0.06
    Activations Density 0.206%

    No Known Activations