© 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. 8635
    Prev
    Next
    INDEX
    Explanations

    commenting on

    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
     Setia
    -0.07
    rtc
    -0.07
    eah
    -0.07
    满åłĤ
    -0.07
    çݰ代çļĦ
    -0.07
    ibold
    -0.07
    ä»Ĭ度ãģ¯
    -0.06
    Tahoma
    -0.06
    utat
    -0.06
    aison
    -0.06
    POSITIVE LOGITS
    ellar
    0.08
    æľīè¿ĩ
    0.07
     дело
    0.07
    quoted
    0.07
    unku
    0.07
    é£ĺé£ĺ
    0.07
    ense
    0.07
    InstanceState
    0.06
    á»ħn
    0.06
     comm
    0.06
    Activations Density 0.003%

    No Known Activations