© 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. 19125
    Prev
    Next
    INDEX
    Explanations

    statistical quantities

    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
    -0.07
    λÏħ
    -0.06
     infinite
    -0.06
     trá»įn
    -0.06
     repet
    -0.06
    彬
    -0.06
    voll
    -0.06
     .
    -0.05
     rallying
    -0.05
    é¦ĸ
    -0.05
    POSITIVE LOGITS
     hoeveel
    0.11
    è¿Ļéĥ¨åĪĨ
    0.10
     aantal
    0.10
     колиÑĩеÑģÑĤво
    0.10
    æľīå¤ļå°ij
    0.10
     кÑĸлÑĮкÑĸÑģÑĤÑĮ
    0.10
    adors
    0.10
     колиÑĩеÑģÑĤва
    0.10
    æķ°éĩıçļĦ
    0.10
    æ¯Ķä¾ĭçļĦ
    0.10
    Activations Density 0.108%

    No Known Activations