© 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. 22103
    Prev
    Next
    INDEX
    Explanations

    distinct, different, unique

    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
    足ä¸įåĩºæĪ·
    -0.10
    efeld
    -0.09
    æĿŁ
    -0.09
    esan
    -0.08
    åıįæĶ»
    -0.08
    ilie
    -0.08
    escu
    -0.08
    eel
    -0.08
    alismo
    -0.08
    pth
    -0.08
    POSITIVE LOGITS
    inct
    0.08
    åľ¨åIJĮä¸Ģ
    0.07
    å¼ĢæĿ¥
    0.07
    ä¸Ķæľī
    0.07
    ä¸Ķä¸į
    0.07
     egym
    0.06
    æĪĸå°ij
    0.06
    нÑij
    0.06
    uk
    0.06
    ä¸Ķ
    0.06
    Activations Density 0.007%

    No Known Activations