© 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. 30338
    Prev
    Next
    INDEX
    Explanations

    protocol definitions or code comments

    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
    BlockSize
    -0.08
    æĭīæĸ¯
    -0.07
    ugend
    -0.07
    سÛĮÙĪÙĨ
    -0.07
    ê±°ëĵłìļĶ
    -0.06
    oj
    -0.06
    alj
    -0.06
    igner
    -0.06
    ht
    -0.06
    QS
    -0.06
    POSITIVE LOGITS
    Ìģ
    0.07
     sein
    0.07
    _MSB
    0.06
    人们对
    0.06
    çĮĽè¿Ľ
    0.06
    comun
    0.06
    åı¯ä»¥çĤ¹åĩ»
    0.06
    плика
    0.06
     Madr
    0.06
    lui
    0.06
    Activations Density 0.174%

    No Known Activations