© 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. 19997
    Prev
    Next
    INDEX
    Explanations

    Jason, White, Heidi, Noah, Rudolph

    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
    她说
    -0.06
    wing
    -0.06
     consistent
    -0.06
    à¹Ħหà¸Ļ
    -0.06
     speculative
    -0.06
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.06
    æ¯Ķå¦Ĥ
    -0.06
    ered
    -0.06
    ä¸Ĭæĸ°
    -0.06
    举è¡ĮçļĦ
    -0.06
    POSITIVE LOGITS
    ianos
    0.10
     himself
    0.09
    -sama
    0.09
     ÐĺвановиÑĩ
    0.08
    åħ¶äºº
    0.08
    åĴĮä»ĸçļĦ
    0.08
    çŃī人çļĦ
    0.08
    epam
    0.08
     Himself
    0.08
    ìĹIJê²Į
    0.08
    Activations Density 0.133%

    No Known Activations