© 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. 2703
    Prev
    Next
    INDEX
    Explanations

    say months

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

    No Comments

    Negative Logits
    [param
    -16.75
    legen
    -15.88
     marginal
    -15.31
    锉
    -14.69
     relativ
    -14.69
    -leg
    -14.69
     reflection
    -14.63
    (len
    -14.56
    .perm
    -14.31
    legt
    -14.06
    POSITIVE LOGITS
     Oct
    54.50
    Oct
    51.00
     Jul
    47.25
     Aug
    46.50
     Sep
    45.50
     Apr
    45.50
     Feb
    45.00
     Jan
    44.50
    Aug
    44.00
     Sept
    43.50
    Activations Density 0.142%

    No Known Activations