© 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. 34578
    Prev
    Next
    INDEX
    Explanations

    inverse, opposite, reverse

    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
    åĪ®
    -0.07
    inox
    -0.07
     év
    -0.07
    äºĮ级å¸Ĥåľº
    -0.07
    第äºĮ次
    -0.07
    .scan
    -0.07
    ür
    -0.07
    äºĮ次
    -0.06
    uen
    -0.06
    ä¸įæĩĪ
    -0.06
    POSITIVE LOGITS
    缸åıį
    0.22
    缸åıįçļĦ
    0.20
    åıį
    0.20
    åıįåIJij
    0.20
    çļĦåıį
    0.19
     inverse
    0.18
     opposite
    0.18
     reverse
    0.18
    åıįè¿ĩæĿ¥
    0.18
    .reverse
    0.18
    Activations Density 0.069%

    No Known Activations