© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    say res

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

    No Comments

    Negative Logits
    rovers
    -16.25
    ccoli
    -14.56
    udded
    -13.06
    oire
    -12.75
    rod
    -12.75
    illary
    -12.56
    ippers
    -12.50
    statt
    -12.50
    罰
    -12.44
    isper
    -12.38
    POSITIVE LOGITS
     res
    104.50
    =res
    98.00
     Res
    98.00
    [res
    97.00
    res
    96.50
    Res
    96.00
    (res
    94.00
    .res
    90.00
    	res
    88.50
    -res
    87.00
    Activations Density 0.499%

    No Known Activations