© 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. 40964
    Prev
    Next
    INDEX
    Explanations

    reversing, swapping, change, polarity, symmetry

    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
     Buckley
    -0.08
    stantiate
    -0.07
    apan
    -0.07
    AGON
    -0.07
    issan
    -0.06
    urve
    -0.06
    urm
    -0.06
    ä¹ĭæľĢ
    -0.06
     stretch
    -0.06
     ext
    -0.06
    POSITIVE LOGITS
     flips
    0.10
     reversal
    0.09
     togg
    0.09
     flipping
    0.09
    change
    0.09
    翻转
    0.08
     sign
    0.08
     polarity
    0.08
     halves
    0.08
    kamp
    0.08
    Activations Density 0.004%

    No Known Activations