© 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. 2574
    Prev
    Next
    INDEX
    Explanations

    古

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

    No Comments

    Negative Logits
    Jeremy
    -18.63
     Jeremy
    -18.13
    妳
    -17.50
    Jess
    -17.25
     ����
    -16.63
    kers
    -16.25
    乙方
    -16.13
     Jess
    -16.00
    itti
    -15.88
     Fucked
    -15.63
    POSITIVE LOGITS
    古
    37.25
     ant
    32.75
     Ant
    27.13
    Ant
    25.13
    _ant
    24.38
    ANT
    23.75
    .ant
    22.75
    ant
    21.25
    抗
    20.88
    古人
    20.88
    Activations Density 0.075%

    No Known Activations