© 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. 14513
    Prev
    Next
    INDEX
    Explanations

    post‑think token

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

    No Comments

    Negative Logits
    sap
    -18.13
    RAP
    -17.50
    strap
    -17.50
    maids
    -17.38
    shan
    -17.38
    ree
    -17.38
    isans
    -17.25
    rimp
    -16.63
    sect
    -16.50
    RIPT
    -16.50
    POSITIVE LOGITS
     Tur
    17.63
     Zwe
    17.50
    avr
    16.88
    勇气
    16.38
    游
    15.94
    Brun
    15.56
     NOR
    15.50
    ovsky
    15.44
     Burg
    15.25
     Barr
    15.19
    Activations Density 0.034%

    No Known Activations