© 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. 27117
    Prev
    Next
    INDEX
    Explanations

    numbers, country names, and foreign words

    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
    æĥħæĦı
    -0.07
    urts
    -0.07
    ÏĨε
    -0.07
    urna
    -0.06
    亲身ä½ĵ
    -0.06
    ä»»
    -0.06
    ake
    -0.06
    ç¬ijè¯Ń
    -0.06
    arendra
    -0.06
    atee
    -0.06
    POSITIVE LOGITS
    accio
    0.07
    uas
    0.07
    çķı
    0.07
    ัà¸ĩ
    0.07
    åĵĹ
    0.07
    ëĭ¹
    0.07
    angkok
    0.06
    çek
    0.06
    urop
    0.06
    <<<
    0.06
    Activations Density 0.007%

    No Known Activations