© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7065
    Prev
    Next
    INDEX
    Explanations

    swapped or reversed concepts

    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
    Negative Logits
    rada
    -0.09
    echa
    -0.09
    DDS
    -0.09
    åİ»æĥ³
    -0.08
    ilding
    -0.08
    åı¯æĺ¯ä¸Ģ
    -0.08
    .addNode
    -0.08
    olato
    -0.08
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.07
    heus
    -0.07
    POSITIVE LOGITS
    交æį¢
    0.20
    äºĴæį¢
    0.19
     swap
    0.18
     swapped
    0.18
     swapping
    0.17
    Swap
    0.17
     Swap
    0.17
    swap
    0.16
     exchange
    0.16
     exchanging
    0.15
    Activations Density 0.067%

    No Known Activations