© 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. 33641
    Prev
    Next
    INDEX
    Explanations

    funding for projects and services

    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
    ndl
    -0.07
    rief
    -0.07
    ä¸ĭæĿ¥äºĨ
    -0.07
     minimized
    -0.07
    å·¥åķĨè¡ĮæĶ¿ç®¡çIJĨå±Ģ
    -0.07
    mien
    -0.07
    éĺ¿å¾·
    -0.07
    foro
    -0.07
    alties
    -0.07
    anies
    -0.07
    POSITIVE LOGITS
     fund
    0.09
    åĪĢåĪĥ
    0.08
    ä¹ĭçĶ¨
    0.08
    ãģ«ä½¿
    0.08
     infrastructure
    0.08
    æĢ¥éľĢ
    0.08
    éľĢè¦ģçļĦ
    0.08
    rastructure
    0.08
     priority
    0.08
     deserving
    0.08
    Activations Density 0.213%

    No Known Activations