© 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. 14566
    Prev
    Next
    INDEX
    Explanations

    say acronyms

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

    No Comments

    Negative Logits
    asa
    -25.38
    asha
    -25.00
    ia
    -24.75
    aan
    -23.75
    asma
    -23.63
    assa
    -23.00
    aza
    -22.63
    za
    -22.50
    asia
    -22.00
    ossa
    -22.00
    POSITIVE LOGITS
     Lift
    13.94
    \Eloquent
    13.44
     Vert
    13.38
    过得
    13.31
    奉
    13.19
    vented
    12.94
    phe
    12.94
    mium
    12.75
     Yemen
    12.56
    逞
    12.56
    Activations Density 0.048%

    No Known Activations