© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14532
    Prev
    Next
    INDEX
    Explanations

    say "2"

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

    No Comments

    Negative Logits
     Doll
    -17.50
    �
    -16.63
     Coll
    -16.00
     Coron
    -15.75
    cor
    -15.50
    ivity
    -15.19
    杳
    -15.06
    York
    -14.94
     Crimson
    -14.63
    orny
    -14.63
    POSITIVE LOGITS
    opa
    17.00
    unted
    16.00
    upported
    15.81
     Cla
    15.69
    ctp
    15.00
    esh
    14.94
    IED
    14.75
     Champ
    14.38
    heap
    14.06
    .breakpoints
    13.81
    Activations Density 0.024%

    No Known Activations