© 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. 2494
    Prev
    Next
    INDEX
    Explanations

    say "stats"

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

    No Comments

    Negative Logits
     �
    -18.13
    伯
    -18.00
     deser
    -17.88
    -state
    -17.63
    des
    -17.13
    Bern
    -17.00
     states
    -16.63
    MER
    -16.25
    states
    -15.88
    	des
    -15.88
    POSITIVE LOGITS
     stats
    44.75
    (stats
    40.50
    stats
    39.50
     Stats
    38.00
    	stats
    37.25
     stat
    36.75
    Stats
    36.75
    /stats
    34.25
    .stats
    34.25
    -stats
    32.75
    Activations Density 0.052%

    No Known Activations