© 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. 56617
    Prev
    Next
    INDEX
    Explanations

    mapping genetic regions and markers

    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
    iltr
    -0.08
    winkel
    -0.08
    streams
    -0.08
    dok
    -0.07
    åıĮæµģ
    -0.07
    ibri
    -0.07
    循çݯ
    -0.07
    çĥŃæ°Ķ
    -0.07
    ä¸įèĩª
    -0.07
    ائÙĦ
    -0.07
    POSITIVE LOGITS
    缸è·Ŀ
    0.08
     intervening
    0.08
     marker
    0.08
     markers
    0.07
     junction
    0.07
     extent
    0.07
    ultz
    0.07
    ä½įç½®
    0.07
    顺
    0.07
     recess
    0.07
    Activations Density 0.018%

    No Known Activations