© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    say "rad"

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

    No Comments

    Negative Logits
     Des
    -17.75
     des
    -17.75
    -des
    -16.75
    Des
    -16.75
    etri
    -16.13
    des
    -15.88
    .cons
    -15.44
    itched
    -15.13
     visita
    -14.69
    visit
    -14.50
    POSITIVE LOGITS
     rad
    74.00
    rad
    73.50
     Rad
    73.00
    Rad
    72.50
    (rad
    72.00
    _rad
    66.00
    .rad
    64.00
    -rad
    63.50
    .Rad
    60.00
    _RAD
    59.00
    Activations Density 0.221%

    No Known Activations