© 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. 2131
    Prev
    Next
    INDEX
    Explanations

    say "er"

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

    No Comments

    Negative Logits
    PTR
    -20.00
     MUT
    -18.75
    _MUT
    -17.88
    玳
    -17.38
     TEMP
    -17.38
     mut
    -17.13
    DIG
    -17.00
    楞
    -16.75
    serial
    -16.50
     genu
    -16.50
    POSITIVE LOGITS
     er
    52.50
    埃
    51.50
     Er
    45.50
    Er
    43.75
     ER
    39.00
    _er
    35.25
    _ER
    34.75
     э
    32.75
    エ
    31.75
    .er
    31.13
    Activations Density 0.036%

    No Known Activations