© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17048
    Prev
    Next
    INDEX
    Explanations

    local PARAM, case, sqrt, Copyright

    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
    øv
    -0.09
    .bi
    -0.08
    éĴŀ
    -0.08
     Bagno
    -0.07
    oney
    -0.07
    .lu
    -0.07
    并åIJĮæŶ
    -0.07
    summ
    -0.07
    ש×ķת
    -0.07
    ç»ıåĬŀ
    -0.07
    POSITIVE LOGITS
    rib
    0.07
    ông
    0.07
     маÑĪи
    0.07
     Smy
    0.06
    erville
    0.06
    ÙĪÙĨس
    0.06
    GBT
    0.06
    prit
    0.06
    á»įa
    0.06
    ronics
    0.06
    Activations Density 0.027%

    No Known Activations