© 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. 1841
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    ourt
    -18.13
    formula
    -16.75
    _DATABASE
    -15.56
    iteDatabase
    -15.50
    Formula
    -15.31
    database
    -15.25
     db
    -15.13
    DATABASE
    -15.06
     formula
    -14.81
    db
    -14.75
    POSITIVE LOGITS
    风
    21.38
     wind
    21.38
     code
    21.25
    碳
    21.25
    コード
    21.13
     winds
    20.75
    -ph
    19.63
     php
    19.38
     coding
    19.13
    Wind
    19.00
    Activations Density 0.318%

    No Known Activations