© 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. 63951
    Prev
    Next
    INDEX
    Explanations

    questions and how/why investigations

    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
     Chec
    -0.07
    é²ľæĺİ
    -0.07
    .partial
    -0.06
    preter
    -0.06
    quate
    -0.06
     zwar
    -0.06
    queda
    -0.06
    ä¸Ģ大
    -0.06
     EITHER
    -0.06
    常常ä¼ļ
    -0.06
    POSITIVE LOGITS
     how
    0.16
     why
    0.13
    æĢİæł·
    0.13
    /how
    0.13
    æľī没æľī
    0.13
     whether
    0.12
     apakah
    0.12
     Ø¢ÛĮا
    0.12
    å¦Ĥä½ķçľĭå¾ħ
    0.12
    为ä»Ģä¹Ī
    0.12
    Activations Density 0.069%

    No Known Activations