© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    say "!"

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

    No Comments

    Negative Logits
    .rpm
    -18.00
    _PB
    -17.38
    =top
    -17.13
    Rotor
    -16.63
     Roma
    -16.50
    roman
    -16.50
    ptom
    -16.25
    ibox
    -16.25
     Maui
    -16.25
    rame
    -15.81
    POSITIVE LOGITS
    副主任
    13.94
    棘
    13.88
    沧
    12.88
     ED
    12.75
    edException
    12.75
    -arm
    12.25
    edian
    12.25
    缣
    12.06
     EFF
    12.06
    ще
    12.00
    Activations Density 0.001%

    No Known Activations