© 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. 26568
    Prev
    Next
    INDEX
    Explanations

    -ion ending

    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
    å±¥
    -0.08
    éľĨ
    -0.07
    tima
    -0.07
    inata
    -0.07
    erra
    -0.07
    ensus
    -0.07
    éĩij马
    -0.07
    شد
    -0.07
    anat
    -0.07
    ادات
    -0.07
    POSITIVE LOGITS
    /ion
    0.08
     ion
    0.08
     electron
    0.07
    -ion
    0.07
     Elect
    0.07
    åĽļ
    0.07
    ologe
    0.07
     nucleus
    0.07
    ä¸Ĭ空
    0.07
    antum
    0.07
    Activations Density 0.006%

    No Known Activations