© 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. 28861
    Prev
    Next
    INDEX
    Explanations

    list or 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
    òi
    -0.09
    baugh
    -0.08
    æºIJåľ°
    -0.07
    isman
    -0.07
    çIJĨæĥ³çļĦ
    -0.07
    abili
    -0.07
    ä¸įæĪIJ
    -0.07
    _suite
    -0.07
    _isr
    -0.07
    ä¸įæĺ¯å¾Ī好
    -0.07
    POSITIVE LOGITS
    åħ¶ä¸ŃåĮħæĭ¬
    0.17
    åĮħæĭ¬äºĨ
    0.13
    ä¸ŃåĮħåIJ«
    0.12
    åĮħåIJ«
    0.12
    åĮħåIJ«äºĨ
    0.11
     includes
    0.11
    ä¹ŁåĮħæĭ¬
    0.11
    åĮħæĭ¬
    0.11
     Including
    0.10
    include
    0.10
    Activations Density 0.235%

    No Known Activations