© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2782
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    乙
    -28.25
     ethical
    -24.50
    乙方
    -23.88
     ret
    -23.75
     ethics
    -23.38
     Ethics
    -23.38
    =obj
    -23.25
     Eth
    -23.25
    ,obj
    -22.75
    丙
    -22.63
    POSITIVE LOGITS
    dictions
    14.75
    imum
    14.25
    antage
    13.81
    ailles
    13.81
    ঙ
    13.69
    EMENT
    13.31
    icontrol
    13.06
    -remove
    13.06
    abee
    13.00
    odic
    12.94
    Activations Density 0.543%

    No Known Activations