© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    sources of influence or inspiration

    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
    åı¯å°±
    -0.07
    æīĢæ¶īåıĬ
    -0.07
    èĤī身
    -0.07
    Mage
    -0.07
     (#
    -0.07
     rout
    -0.07
    åħ¨ä½ĵåѦçĶŁ
    -0.07
    çĶ¨ä½ľäººåIJį
    -0.07
    åIJįåī¯
    -0.07
    ä¸İä¼Ĺ
    -0.07
    POSITIVE LOGITS
    æĿ¥èĩª
    0.11
    åĢŁéī´
    0.11
     previous
    0.10
    æĿ¥èĩªäºİ
    0.10
     influences
    0.10
     predecessors
    0.09
    previous
    0.09
     traditional
    0.09
    ä¼łç»Ł
    0.09
    ä¼łç»ŁçļĦ
    0.09
    Activations Density 0.375%

    No Known Activations