© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 2073
    Prev
    Next
    INDEX
    Explanations

    say "exec"

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

    No Comments

    Negative Logits
     Pot
    -21.00
    装置
    -20.00
    pot
    -19.50
    Pot
    -18.50
    _SIM
    -16.88
    _pot
    -16.38
    千
    -16.38
     pert
    -15.63
     Pert
    -15.50
    .den
    -15.31
    POSITIVE LOGITS
     exec
    45.75
    exec
    42.75
    .exec
    41.00
    Exec
    39.25
     Exec
    37.00
    _exec
    33.25
    /exec
    32.75
    	exec
    30.75
    .Exec
    30.75
     executive
    28.88
    Activations Density 0.051%

    No Known Activations