© 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. 25756
    Prev
    Next
    INDEX
    Explanations

    characteristics and properties

    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
    íĬ¸ë¡ľ
    -0.09
    WithTag
    -0.09
    джи
    -0.08
     Monti
    -0.08
    OfType
    -0.08
    æĺ¯ä½ķåIJ«ä¹ī
    -0.08
    CursorPosition
    -0.08
    ÑĦелÑĮ
    -0.08
    ]+)/
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    POSITIVE LOGITS
     resemble
    0.12
     resembles
    0.12
    ä¸Ĭä¸İ
    0.12
     resembled
    0.11
    类似äºİ
    0.11
     Similar
    0.11
    è¿Ļä¸İ
    0.10
     identical
    0.10
     similar
    0.10
     matches
    0.10
    Activations Density 0.299%

    No Known Activations