© 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. 45044
    Prev
    Next
    INDEX
    Explanations

    all, every, each

    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
    ä»įæĺ¯
    -0.07
    Wrong
    -0.06
    lee
    -0.06
    ä¾ĿçĦ¶æĺ¯
    -0.06
    wrong
    -0.06
    éĩij森
    -0.06
    è¿Ķ
    -0.06
    ild
    -0.06
    ä»įçĦ¶æĺ¯
    -0.06
    ä¸İåѦçĶŁ
    -0.06
    POSITIVE LOGITS
    é½IJåħ¨
    0.13
    é½IJåħ¨çļĦ
    0.12
    à¸Ħรà¸ļ
    0.12
    缺ä¸Ģä¸įåı¯
    0.11
    -required
    0.10
    俱åħ¨
    0.10
    å®Įæķ´çļĦ
    0.10
    ä¸ĢåºĶ俱åħ¨
    0.10
    å®Įæķ´åľ°
    0.10
    缺ä¸Ģ
    0.09
    Activations Density 0.076%

    No Known Activations