© 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. 24964
    Prev
    Next
    INDEX
    Explanations

    adding or addition

    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
    лиÑĤ
    -0.08
    æĪij第ä¸Ģ次
    -0.07
    erdale
    -0.07
    大计
    -0.07
    åĥıä¸Ģåıª
    -0.07
    _again
    -0.07
    åĶ¯ä¸Ģä¸Ģ家
    -0.07
    缸åħ³äºĭå®ľ
    -0.07
    amer
    -0.07
    大好
    -0.07
    POSITIVE LOGITS
     hinzu
    0.18
     added
    0.16
    éĻĦåĬł
    0.15
    é¢Ŀå¤ĸçļĦ
    0.15
    é¢Ŀå¤ĸ
    0.15
     thêm
    0.15
     Added
    0.14
    æ·»åĬł
    0.14
    added
    0.13
     adds
    0.13
    Activations Density 0.213%

    No Known Activations