© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    pent/hex prefixes

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

    No Comments

    Negative Logits
    oref
    -17.38
    erb
    -16.88
     uncert
    -16.38
    (var
    -16.13
     char
    -16.13
     emulation
    -15.94
    Controllers
    -15.75
    frame
    -15.63
    [char
    -15.56
    .frame
    -15.31
    POSITIVE LOGITS
     Pent
    72.50
     pent
    72.00
    pent
    61.50
     hex
    60.50
    hex
    59.25
     Hex
    55.25
    Hex
    54.00
    (hex
    50.00
    _hex
    49.25
     HEX
    46.75
    Activations Density 0.038%

    No Known Activations