© 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. 51838
    Prev
    Next
    INDEX
    Explanations

    suffixes like -ation, -itized, -ensis

    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
    æľĢ为
    -0.07
     become
    -0.06
    oles
    -0.06
    é¡¿
    -0.06
    V
    -0.06
    ÑģоÑĤа
    -0.06
    Ú¯
    -0.05
    ãĤ¬
    -0.05
    p
    -0.05
     Coleman
    -0.05
    POSITIVE LOGITS
    rone
    0.09
    顾åIJįæĢĿä¹ī
    0.09
    htub
    0.08
    urve
    0.08
    æīĢæľīç«łèĬĤ
    0.08
    ovem
    0.07
    MMC
    0.07
    kills
    0.07
    éºĴ
    0.07
     [âĢ¦]
    0.07
    Activations Density 0.461%

    No Known Activations