© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15485
    Prev
    Next
    INDEX
    Explanations

    say boom-and-bust

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _DI
    -16.63
    フォー
    -16.63
    _ISO
    -16.00
    ISO
    -15.94
    ardin
    -15.69
    SID
    -15.69
    长三角
    -15.69
    wdx
    -15.44
    瀍
    -15.31
     Salisbury
    -15.25
    POSITIVE LOGITS
     Crash
    26.13
    boom
    25.50
     Boom
    25.25
     boom
    23.63
     crash
    23.13
    Boom
    22.63
     crashes
    21.88
     Bubble
    21.63
     bubble
    20.25
     bubbles
    20.25
    Activations Density 0.187%

    No Known Activations