© 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. 55758
    Prev
    Next
    INDEX
    Explanations

    accepted dates

    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
    榻
    -0.06
     reflection
    -0.06
    ิà¸ļ
    -0.06
    Ag
    -0.06
    ä½ı
    -0.06
     reflecting
    -0.06
    çĭIJ
    -0.06
    æİ¥åıĹ
    -0.06
    격
    -0.06
    æŃ¢
    -0.06
    POSITIVE LOGITS
     GRO
    0.07
    ÙİÙijا
    0.07
    emo
    0.07
    .Localization
    0.07
    urement
    0.07
    Ú©ÙĦ
    0.07
    ãĥĬãĥł
    0.07
    otify
    0.07
    ventura
    0.07
    alink
    0.07
    Activations Density 0.005%

    No Known Activations