© 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. 2887
    Prev
    Next
    INDEX
    Explanations

    say Eth

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

    No Comments

    Negative Logits
     Facility
    -22.38
    Pat
    -21.63
    (pat
    -21.13
     facility
    -20.63
    .pat
    -20.50
    pat
    -20.00
    (iter
    -19.50
     Tat
    -19.13
    PAT
    -19.00
     Digit
    -18.88
    POSITIVE LOGITS
    套
    18.88
     MER
    16.75
     Ethics
    16.13
    rem
    15.75
     Simulation
    15.63
     pres
    15.44
     ETH
    15.19
     Eth
    15.13
    _dem
    15.00
    pres
    14.81
    Activations Density 0.163%

    No Known Activations