© 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. 26988
    Prev
    Next
    INDEX
    Explanations

    specific entities or types

    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
    å¹³æ¹ĸ
    -0.08
    åŁ¼
    -0.07
     seam
    -0.07
    ä¸Ń没æľī
    -0.07
    à¸ļà¹īาà¸ĩ
    -0.06
    é£İè½»
    -0.06
    Ò¡
    -0.06
    _widgets
    -0.06
    éĢIJ
    -0.06
    bach
    -0.06
    POSITIVE LOGITS
    çī¹å®ļçļĦ
    0.13
    çī¹å®ļ
    0.13
    æŁIJä¸Ģ
    0.11
    çī¹å®ļãģ®
    0.11
     опÑĢеделенного
    0.10
     íĬ¹ìłķ
    0.10
     tertentu
    0.09
    æŁIJ个
    0.09
     опÑĢеделенной
    0.09
     corresponding
    0.09
    Activations Density 0.111%

    No Known Activations