© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    math expressions

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

    No Comments

    Negative Logits
     Pete
    -20.63
     Pet
    -19.75
    提案
    -18.75
    Pet
    -18.00
     proposal
    -17.88
    Cur
    -17.25
    Leg
    -16.75
     Et
    -16.75
     pet
    -16.63
    et
    -16.50
    POSITIVE LOGITS
    IMAL
    16.88
     apparatus
    16.75
    SENT
    16.75
    (Enum
    16.63
     harness
    16.50
    机构
    16.25
     marg
    16.13
     modal
    16.00
     margins
    15.50
    uale
    15.44
    Activations Density 0.049%

    No Known Activations