© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15013
    Prev
    Next
    INDEX
    Explanations

    say f

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

    No Comments

    Negative Logits
    drs
    -15.81
    unned
    -15.31
    ящих
    -14.25
     обраща
    -13.88
    (rad
    -13.56
    empor
    -13.50
    orda
    -13.06
    obox
    -12.94
    亳
    -12.94
    visor
    -12.81
    POSITIVE LOGITS
    f
    45.50
    -f
    41.75
     f
    40.25
    _f
    39.00
    F
    38.75
    ф
    37.75
    ｆ
    36.50
    	f
    36.00
    .f
    35.50
    𝑓
    35.50
    Activations Density 0.606%

    No Known Activations