© 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. 14868
    Prev
    Next
    INDEX
    Explanations

    Armin Ronacher, Phan Thi Kim Phuc, Router

    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
    æľĭ
    -0.07
    elib
    -0.07
     pret
    -0.06
    å·¾
    -0.06
     (âĢŀ
    -0.06
    éĢģ
    -0.06
    ignon
    -0.06
    itin
    -0.06
    udit
    -0.06
    eref
    -0.05
    POSITIVE LOGITS
    临走
    0.09
    涨åĬ¿
    0.08
    *@
    0.08
    ìĹ
    0.08
    xeb
    0.08
    ëģĦ
    0.08
    isting
    0.07
    <?=
    0.07
    æıª
    0.07
    åIJĥä½ı
    0.07
    Activations Density 0.003%

    No Known Activations