© 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. 2766
    Prev
    Next
    INDEX
    Explanations

    say "lime"

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

    No Comments

    Negative Logits
     ter
    -19.13
    _ter
    -18.13
     Mut
    -18.13
    Ter
    -18.00
     Ter
    -17.75
     TER
    -17.63
    =ax
    -17.38
    .gen
    -17.25
    _gen
    -16.88
     genotype
    -16.50
    POSITIVE LOGITS
     lime
    41.25
     Lime
    36.25
     lim
    34.25
     Lim
    34.25
    lime
    33.50
    Lim
    33.00
    lim
    32.00
     Lima
    24.00
     limb
    23.38
    _lim
    22.63
    Activations Density 0.035%

    No Known Activations