© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14600
    Prev
    Next
    INDEX
    Explanations

    an AI assistant

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

    No Comments

    Negative Logits
     Emit
    -18.38
     América
    -17.00
    ORB
    -16.88
    得意
    -16.63
     paramName
    -16.38
    (hand
    -16.13
    arry
    -16.13
    .TryParse
    -16.13
    米尔
    -16.00
    FromArray
    -15.88
    POSITIVE LOGITS
     Dolphins
    15.25
     Her
    15.25
    *B
    13.69
    Abstract
    12.69
    House
    12.63
     dolphins
    12.63
    Her
    12.31
    B
    12.25
     Eu
    12.19
    js
    12.00
    Activations Density 0.002%

    No Known Activations