© 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. 31083
    Prev
    Next
    INDEX
    Explanations

    vascularity, sound, luminous, spun, salinity

    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
    atang
    -0.07
    anager
    -0.07
    家
    -0.07
    ×Ļת
    -0.07
    ider
    -0.07
    anggap
    -0.07
    اÙĦÙĬا
    -0.06
    rup
    -0.06
    icação
    -0.06
    -turned
    -0.06
    POSITIVE LOGITS
    çĶļèĩ³è¿ŀ
    0.07
    并ä¸Ķè¿ĺ
    0.07
    æĥ«
    0.07
    ajer
    0.06
    áĥľáĥĺ
    0.06
    ç»ıæŁ¥
    0.06
    icks
    0.06
    ãĥIJãĥ©
    0.06
    ä½łçļĦæľĭåıĭ
    0.06
    çĶļèĩ³æľīäºĽ
    0.06
    Activations Density 0.050%

    No Known Activations