© 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. 23410
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence starters

    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
    Bre
    -0.07
    rek
    -0.07
    éĽ
    -0.06
    TRE
    -0.06
    两头
    -0.06
    rana
    -0.06
    ç®
    -0.06
    dze
    -0.06
    å·¢
    -0.06
    ä¸ĥæĺŁ
    -0.06
    POSITIVE LOGITS
    nTo
    0.08
    ÙĪÙī
    0.08
    ева
    0.08
     zweit
    0.07
    ÑĮе
    0.07
    elten
    0.07
    eva
    0.07
    å°±æĭ¿
    0.07
    åħ¶äºĮ
    0.07
    æĭ¥æľīçĿĢ
    0.07
    Activations Density 0.167%

    No Known Activations