© 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. 14548
    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
    Ale
    -23.75
     Ale
    -23.00
    /ne
    -22.25
    če
    -22.13
    zee
    -21.50
     geme
    -21.25
    _ne
    -21.13
    exe
    -21.00
    reme
    -20.88
    ne
    -20.75
    POSITIVE LOGITS
    aptor
    15.44
    illard
    15.25
    aptors
    15.25
    ld
    14.81
    rd
    14.13
    avid
    13.81
    打
    13.75
    lias
    13.69
    -l
    13.63
    til
    13.56
    Activations Density 0.009%

    No Known Activations