© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    Pers

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

    No Comments

    Negative Logits
     antic
    -17.13
    防
    -16.88
    =val
    -16.25
    emi
    -16.00
    uste
    -15.75
    igate
    -15.63
    校
    -15.44
     rec
    -15.25
    asic
    -15.06
    ******
↵
    -15.06
    POSITIVE LOGITS
     Pers
    52.50
    Pers
    49.25
    Perm
    48.25
     perm
    48.25
     pers
    45.25
    perm
    44.75
     pert
    44.00
     Pert
    43.75
    pers
    43.50
     Perm
    42.75
    Activations Density 0.086%

    No Known Activations