© 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. 30606
    Prev
    Next
    INDEX
    Explanations

    go:home

    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
    emus
    -0.07
    gern
    -0.06
    feeds
    -0.06
    寨
    -0.06
    emar
    -0.06
    åĪĩå®ŀåģļåĪ°
    -0.06
    eon
    -0.06
    huizen
    -0.06
    è¾īçħĮçļĦ
    -0.06
    uarte
    -0.06
    POSITIVE LOGITS
    å¤§åľ°
    0.09
    çīĪ
    0.08
    çıĤ
    0.08
    itat
    0.07
    versions
    0.07
    é¦ĸéķ¿
    0.07
    еÑĤен
    0.07
     полож
    0.07
    dos
    0.07
    åİĨ
    0.07
    Activations Density 0.003%

    No Known Activations