© 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. 56046
    Prev
    Next
    INDEX
    Explanations

    symbols and code delimiters

    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
    åĽ¢åĽ¢
    -0.08
    andy
    -0.07
    åįķåIJij
    -0.07
    ier
    -0.06
    nat
    -0.06
    ase
    -0.06
    å¼Ģ
    -0.06
    ply
    -0.06
    æĪª
    -0.06
    rase
    -0.06
    POSITIVE LOGITS
    akens
    0.09
    继ç»Ń沿
    0.08
    째
    0.08
    ä»»ä½ķä¸ľè¥¿
    0.08
     succeeding
    0.08
    udid
    0.08
    ichte
    0.08
    ･･･
    0.08
    é«ĺè°ĥ
    0.07
    setState
    0.07
    Activations Density 0.007%

    No Known Activations