© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2233
    Prev
    Next
    INDEX
    Explanations

    say "mock"

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

    No Comments

    Negative Logits
    集成
    -19.00
     integration
    -18.00
    (cur
    -17.13
    cur
    -16.63
     capital
    -16.38
    Integration
    -16.25
     Capital
    -16.13
    integration
    -16.13
    ertest
    -16.00
     Integration
    -15.94
    POSITIVE LOGITS
    PET
    16.88
     PET
    15.13
    KE
    15.06
    dia
    15.00
    Demo
    14.75
    ceb
    14.56
    agara
    14.31
     Memo
    14.25
     Morph
    14.19
    Animating
    13.88
    Activations Density 0.005%

    No Known Activations