© 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. 56174
    Prev
    Next
    INDEX
    Explanations

    Microsoft Corporation

    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
    ège
    -0.08
     sekt
    -0.07
    åĴ¬çĿĢ
    -0.07
    微信æī«çłģ
    -0.07
    ums
    -0.07
    ards
    -0.07
    æķ£çļĦ
    -0.07
    è¾¾æĸ¯
    -0.07
    cia
    -0.07
    yg
    -0.07
    POSITIVE LOGITS
    ãģ¨ãĤĤãģ«
    0.07
     напо
    0.07
     Shr
    0.07
    åħ¨èĥľ
    0.07
    .Config
    0.07
    곡
    0.07
    产åĵģ
    0.06
    æ³½æ°ij
    0.06
    ิà¸Ķ
    0.06
     Armour
    0.06
    Activations Density 0.001%

    No Known Activations