© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26747
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with parentheses

    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
    gon
    -0.07
    amis
    -0.07
    éĢīæĭ©åĴĮ
    -0.07
    PIO
    -0.07
    ãĥªãĤ¨
    -0.07
    _SM
    -0.06
    obot
    -0.06
    .choices
    -0.06
    æĥħ
    -0.06
    оÑģÑĤо
    -0.06
    POSITIVE LOGITS
    æ·±çŁ¥
    0.07
     Gates
    0.07
    .ms
    0.07
    erator
    0.06
    岸
    0.06
    illary
    0.06
    ATYPE
    0.06
     ayl
    0.06
    orde
    0.06
    çĭĹä»Ķ
    0.06
    Activations Density 0.011%

    No Known Activations