© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14666
    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
    @js
    -18.25
    crement
    -17.00
    FAULT
    -17.00
    瓷砖
    -16.88
    uclear
    -16.75
    _fault
    -16.50
    criptors
    -16.38
    迕
    -16.38
    nbr
    -16.38
    ropy
    -16.25
    POSITIVE LOGITS
     bil
    19.25
     bel
    16.00
    gif
    15.25
    箫
    15.25
     Shin
    15.25
     Pol
    15.19
    .sig
    14.88
    Wilson
    14.75
     Bel
    14.56
    пол
    14.50
    Activations Density 0.140%

    No Known Activations