© 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. 38009
    Prev
    Next
    INDEX
    Explanations

    code delimiters or symbols

    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
    ifact
    -0.09
    colo
    -0.09
    _tac
    -0.08
    cak
    -0.08
    æľīæĿĥä¿ĿçķĻ
    -0.08
    ä¸Ŀä¸Ŀ
    -0.08
    ëĤĺë§Ī
    -0.08
    orsch
    -0.08
    zzle
    -0.08
    -alist
    -0.08
    POSITIVE LOGITS
    åIJĦèĩª
    0.08
    åľ¨ä¸Ģèµ·
    0.08
    åħ±åIJĮ
    0.08
    åIJĦèĩªçļĦ
    0.08
     together
    0.08
    åIJĪ
    0.07
    é½IJ
    0.06
    åĪ°ä¸Ģèµ·
    0.06
     Together
    0.06
    åľ¨ä¸Ģèµ·çļĦ
    0.06
    Activations Density 0.013%

    No Known Activations