© 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. 8425
    Prev
    Next
    INDEX
    Explanations

    documentation

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    碴
    -0.07
    çī¹åĪ«æĺ¯å¯¹
    -0.06
    inarie
    -0.06
    знаÑĩ
    -0.06
    /from
    -0.06
    ัà¸į
    -0.06
     küm
    -0.06
    spartner
    -0.06
    ä¸ĵç²¾çī¹æĸ°
    -0.06
    POSITIVE LOGITS
    两åѦä¸Ģåģļ
    0.09
    ä¼ĹæīĢåij¨çŁ¥
    0.09
    ়
    0.07
    åı¬
    0.07
     Juve
    0.07
    ergestellt
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
     usufruire
    0.07
    ÙĩÙħا
    0.07
    inheritDoc
    0.07
    Activations Density 0.429%

    No Known Activations