© 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. 42736
    Prev
    Next
    INDEX
    Explanations

    multiple parts

    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
    porta
    -0.08
     indire
    -0.07
    owie
    -0.07
    ulette
    -0.07
    å°ıå°ıçļĦ
    -0.07
    ä¸į误
    -0.07
    çĴĢ
    -0.07
    ä»»éĩį
    -0.07
    ataka
    -0.07
    åħ¨ç½ij
    -0.07
    POSITIVE LOGITS
    ç»ĦæĪIJ
    0.10
     distinct
    0.10
    ç»ĦæĪIJçļĦ
    0.10
     composition
    0.10
    åľ¨éĩĮéĿ¢
    0.09
    è¤ĩæķ°ãģ®
    0.09
    ä¸įåIJĮçļĦ
    0.09
     components
    0.09
    æĭ¼
    0.09
    æĪIJåĪĨ
    0.08
    Activations Density 0.091%

    No Known Activations