© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    say "penalty"

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

    No Comments

    Negative Logits
    (dim
    -18.50
     config
    -18.38
     dimension
    -17.88
    	config
    -17.63
     configs
    -17.50
    .getConfig
    -17.38
    config
    -16.13
    dimension
    -16.13
    Leg
    -15.88
    Configs
    -15.88
    POSITIVE LOGITS
    Pen
    58.25
    pen
    57.25
     Pen
    55.25
     penalty
    53.75
     pen
    53.50
     Penalty
    50.75
    _pen
    50.50
     penalties
    47.75
    .pen
    45.25
    笔
    45.00
    Activations Density 0.091%

    No Known Activations