© 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. 15198
    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
     Buckley
    -17.38
     Roberts
    -17.25
     Whitney
    -17.13
    CBS
    -17.00
    SpinBox
    -16.38
    edBy
    -16.25
    华润
    -16.00
    ocoder
    -15.88
    IPAddress
    -15.88
     Mustang
    -15.75
    POSITIVE LOGITS
     TIM
    16.63
    胰
    16.13
     vit
    16.00
    二期
    15.81
     tir
    15.63
    ｐ
    15.56
    .trace
    15.50
    .fire
    15.31
     DAM
    15.13
    .getD
    15.06
    Activations Density 0.092%

    No Known Activations