© 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. 2386
    Prev
    Next
    INDEX
    Explanations

    say "Brad" names

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

    No Comments

    Negative Logits
    装置
    -21.00
     pert
    -19.38
     Pert
    -18.75
     perm
    -18.50
    器
    -18.38
    pert
    -18.13
     app
    -17.63
     Mut
    -17.38
     reli
    -17.13
    PERT
    -16.88
    POSITIVE LOGITS
     Brad
    43.00
    Brad
    42.75
     Bradley
    35.25
     Bradford
    25.38
    伯
    23.25
    乙方
    21.63
     Ber
    21.50
     btn
    20.88
    $str
    20.88
    甲方
    20.50
    Activations Density 0.051%

    No Known Activations