© 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. 27531
    Prev
    Next
    INDEX
    Explanations

    coordinate systems and terminology

    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
    æ¯ĶæĪij
    -0.07
    被æĪij
    -0.06
    æľºç¼ĺ
    -0.06
    åºĶæĮī
    -0.06
    actor
    -0.06
    syl
    -0.06
    åħľ
    -0.06
    èĢĮçŁ¥
    -0.06
    abu
    -0.06
    .sort
    -0.06
    POSITIVE LOGITS
    adou
    0.09
    geld
    0.08
    onda
    0.08
    表示
    0.08
    rightness
    0.08
    åħ¨éĥ¨è¯Ħ论
    0.07
    -Version
    0.07
    çļĦä¸ĸçķĮéĩĮ
    0.07
    ioen
    0.07
    enstr
    0.07
    Activations Density 0.007%

    No Known Activations