© 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. 14727
    Prev
    Next
    INDEX
    Explanations

    say suffixes

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

    No Comments

    Negative Logits
    D
    -17.13
     d
    -16.00
     dol
    -15.88
    "d
    -15.63
    .d
    -15.38
    d
    -15.19
    uis
    -15.06
    -u
    -14.81
    cls
    -14.56
    зи
    -14.56
    POSITIVE LOGITS
    idl
    18.00
    ån
    17.75
    ibi
    17.25
    nik
    17.00
    nge
    16.88
     rub
    16.63
    ration
    16.50
    ebra
    16.00
    rated
    15.69
    SPEC
    15.56
    Activations Density 0.503%

    No Known Activations