© 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. 21618
    Prev
    Next
    INDEX
    Explanations

    filenames and identifiers

    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
    笨
    -0.06
    端起
    -0.06
    æī§è¡Į
    -0.06
    zze
    -0.06
    顺
    -0.06
    æīĢéľĢçļĦ
    -0.06
    lien
    -0.06
    åı·
    -0.06
    .space
    -0.06
     Merah
    -0.06
    POSITIVE LOGITS
    RelativeTo
    0.08
    ساÙĨÛĮ
    0.08
    _OBS
    0.08
    ersp
    0.07
    uet
    0.07
    á»ijp
    0.07
    Ĵáŀ
    0.07
     Newtown
    0.07
    ä¹ĭéŁ³
    0.07
    åı¯æ¢¦
    0.07
    Activations Density 0.027%

    No Known Activations