© 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. 14635
    Prev
    Next
    INDEX
    Explanations

    containers

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

    No Comments

    Negative Logits
    yms
    -18.38
    acas
    -18.00
    orrect
    -17.63
    ickers
    -16.63
     Wyn
    -16.63
     Sher
    -16.50
    Sher
    -16.13
    ONS
    -16.13
     CONS
    -16.13
    YNC
    -16.00
    POSITIVE LOGITS
    igh
    13.19
    信用
    13.13
     seam
    12.94
    lad
    12.38
    CDATA
    12.19
    ٫
    11.94
     financially
    11.81
     stack
    11.75
    ″
    11.50
     dye
    11.38
    Activations Density 0.060%

    No Known Activations