© 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. 14432
    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
    xb
    -27.13
    xc
    -26.13
    xdf
    -26.00
    xBA
    -25.75
    xba
    -25.38
    xf
    -25.25
    xbe
    -24.88
    xbc
    -24.63
    xe
    -24.38
    xs
    -24.38
    POSITIVE LOGITS
    tern
    20.50
    GOR
    18.13
    SOR
    16.75
    纠
    16.38
    OOT
    16.38
    orris
    16.38
    etus
    15.56
    MAL
    15.38
    VERN
    15.13
    eor
    15.06
    Activations Density 0.007%

    No Known Activations