© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    say "mod"

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

    No Comments

    Negative Logits
     seg
    -18.88
     facility
    -18.38
    利
    -18.25
    Seg
    -18.13
    (fil
    -18.00
     pen
    -17.88
    seg
    -17.50
    repo
    -17.50
    Segments
    -17.38
    [char
    -16.75
    POSITIVE LOGITS
    (Mod
    33.25
     Mod
    32.25
    Mod
    30.75
    MOD
    30.50
     mod
    30.38
    mod
    30.13
    (mod
    29.75
    .mod
    29.50
    _mod
    29.25
     MOD
    28.25
    Activations Density 0.109%

    No Known Activations