© 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. 51792
    Prev
    Next
    INDEX
    Explanations

    variable frequency, success, size, effects, etc

    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
    åį³çĶ¨
    -0.07
    æĪĸå°ij
    -0.07
    ui
    -0.07
    ãģĤãģŁ
    -0.06
    ÑĢÑĥк
    -0.06
    ä¸İä¼Ĺä¸įåIJĮ
    -0.06
     Cib
    -0.06
    roku
    -0.06
    é¦ĸæ¬¡åľ¨
    -0.06
    akai
    -0.06
    POSITIVE LOGITS
     depending
    0.14
     dependendo
    0.11
    depending
    0.11
     dependiendo
    0.10
     Depending
    0.10
     ranging
    0.10
    ä¸įåIJĮç¨ĭ度çļĦ
    0.10
    åıĸåĨ³äºİ
    0.10
    —from
    0.10
    Depending
    0.09
    Activations Density 0.155%

    No Known Activations