© 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. 23246
    Prev
    Next
    INDEX
    Explanations

    vector math symbols

    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
    al
    -0.06
    8
    -0.06
    1
    -0.06
    6
    -0.06
     no
    -0.06
     ...
    -0.06
    èĻ
    -0.06
    9
    -0.06
     ↵
    -0.06
    -0.05
    POSITIVE LOGITS
    eldes
    0.10
    å®Ŀå®Ŀ们
    0.09
    çļĦ人æĿ¥è¯´
    0.09
    åIJĪåIJĮæŶ
    0.09
    emos
    0.09
    èģĮå®Ī
    0.09
    人æĿ¥è¯´
    0.09
    edig
    0.09
    ankind
    0.09
    ī´
    0.09
    Activations Density 0.014%

    No Known Activations