© 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. 45990
    Prev
    Next
    INDEX
    Explanations

    symmetry, flip, mirror, swapping

    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
    æĭĶåĩº
    -0.07
    æ±Ĥç²¾
    -0.07
    rent
    -0.07
    æīĵèµ·
    -0.07
    å¼Ľ
    -0.07
    èģĶç½ij
    -0.07
    ento
    -0.07
    éĤĢæĤ¨
    -0.07
    abu
    -0.07
    æĶ¾å¼Ģ
    -0.07
    POSITIVE LOGITS
     symmetry
    0.11
    ç¿»
    0.10
     flip
    0.10
     flips
    0.10
    keh
    0.09
    对称
    0.09
     flipping
    0.09
    åij¨æľŁ
    0.09
    flip
    0.08
     swapping
    0.08
    Activations Density 0.010%

    No Known Activations