© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    say "x"

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

    No Comments

    Negative Logits
    aData
    -17.13
    efa
    -16.63
    adata
    -16.00
    cred
    -15.94
    ADATA
    -15.94
     xe
    -15.31
     axe
    -15.13
    crew
    -15.06
    aeda
    -14.88
    dfa
    -14.56
    POSITIVE LOGITS
    ortal
    16.75
    tip
    15.50
     Pom
    15.38
    Tip
    15.31
    ivet
    15.25
    Listen
    14.94
    POR
    14.81
    iry
    14.75
    tom
    14.75
    tpl
    14.69
    Activations Density 0.006%

    No Known Activations