© 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. 8912
    Prev
    Next
    INDEX
    Explanations

    variable declarations with parentheses

    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
    ellig
    -0.06
    ä½ĨæĦ¿
    -0.06
    .im
    -0.06
    人ä¸İ人
    -0.06
    OMEM
    -0.06
    ä¸įæĸŃæĶ¹è¿Ľ
    -0.06
     Heck
    -0.06
     Gia
    -0.06
    ingen
    -0.06
    çĮİ
    -0.06
    POSITIVE LOGITS
    loo
    0.09
    ENSE
    0.08
     Parkway
    0.08
    èĢĮèĩ³
    0.08
    fsp
    0.08
    atriz
    0.08
    ç«Ļç«Ļ
    0.08
    ähler
    0.07
    è·¨è¶Ĭå¼ı
    0.07
    æī¦
    0.07
    Activations Density 0.027%

    No Known Activations