© 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. 42098
    Prev
    Next
    INDEX
    Explanations

    inverse decreasing motion

    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
    å¢ŀå¹ħ
    -0.08
    åĨĴçĿĢ
    -0.07
    åĪĨå¼Ģ
    -0.06
    举
    -0.06
    growth
    -0.06
    Expansion
    -0.06
    åĬłä»·
    -0.06
    åĬłå¼ºå¯¹
    -0.06
     growth
    -0.06
     forwards
    -0.06
    POSITIVE LOGITS
     invers
    0.15
     inverse
    0.15
    inverse
    0.14
    Inverse
    0.13
     decreasing
    0.13
    éĢĨ
    0.13
    çļĦåıį
    0.12
    åıįåIJij
    0.12
    éĻį
    0.12
    .inverse
    0.12
    Activations Density 0.075%

    No Known Activations