© 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. 2805
    Prev
    Next
    INDEX
    Explanations

    say dev

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

    No Comments

    Negative Logits
    积分
    -15.25
     Eric
    -15.00
    etric
    -14.69
     Gilbert
    -14.44
    ional
    -14.31
     captures
    -14.19
     BER
    -14.00
     Capt
    -13.94
    Capt
    -13.88
    ohn
    -13.69
    POSITIVE LOGITS
     dev
    96.00
     Dev
    90.00
    Dev
    87.50
    dev
    87.00
    (dev
    81.00
    	dev
    80.00
    .dev
    77.00
    _dev
    76.00
    /dev
    73.00
     DEV
    72.00
    Activations Density 0.202%

    No Known Activations