© 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. 23399
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
     Suns
    -0.08
    allery
    -0.08
    imon
    -0.08
    ì±Ħ
    -0.07
    okrat
    -0.07
    åde
    -0.07
    ä»ĸæĬĬ
    -0.07
    หม
    -0.07
    éķ£
    -0.07
     تÙĤرÙĬب
    -0.07
    POSITIVE LOGITS
    _DIRECTION
    0.07
    æĪij以
    0.07
    æľĶ
    0.07
    åıįåIJij
    0.07
    éĢĨåIJij
    0.07
    itzen
    0.07
     symmetry
    0.07
    udem
    0.06
     honoured
    0.06
     sym
    0.06
    Activations Density 0.003%

    No Known Activations