© 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. 57918
    Prev
    Next
    INDEX
    Explanations

    clusters and patches

    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
    åħ¨åĽ½äººæ°ij
    -0.08
     Plain
    -0.07
    ä¸įåĩı
    -0.07
    ally
    -0.07
    å¼Ĥçī©
    -0.07
    ackers
    -0.06
    plain
    -0.06
    ALLY
    -0.06
    é½IJ
    -0.06
    Unis
    -0.06
    POSITIVE LOGITS
    大大å°ıå°ıçļĦ
    0.10
    ä¸Ģ个ä¸Ģ个
    0.09
     randomly
    0.09
     interconnected
    0.09
     clusters
    0.08
     small
    0.08
    ä¸Ģ个个
    0.08
     intermitt
    0.08
     patches
    0.08
     structures
    0.08
    Activations Density 0.051%

    No Known Activations