© 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. 32634
    Prev
    Next
    INDEX
    Explanations

    interferometer, interferometry

    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
    ái
    -0.07
    èĶĵ延
    -0.07
    iales
    -0.07
    åģļé¢ĺ
    -0.07
    èIJĮèĬ½
    -0.07
    katan
    -0.06
     Somm
    -0.06
    aleza
    -0.06
    allas
    -0.06
    /plugin
    -0.06
    POSITIVE LOGITS
     optical
    0.09
     Optical
    0.09
     interfer
    0.09
    _paths
    0.08
    difference
    0.08
    åĪĨåħī
    0.08
     getPath
    0.08
    åıĮèĩĤ
    0.07
    è·¯çļĦ
    0.07
     detectors
    0.07
    Activations Density 0.030%

    No Known Activations