© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    仲

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

    No Comments

    Negative Logits
    Gen
    -19.38
     genotype
    -18.00
     \`
    -17.63
    -ret
    -17.38
    零售
    -17.13
     genie
    -17.00
    (gen
    -16.88
    (dev
    -16.88
    dev
    -16.63
     gen
    -16.63
    POSITIVE LOGITS
    仲
    47.75
     mod
    34.75
     Mod
    34.50
    mod
    33.25
     MOD
    32.50
    Mod
    32.25
    .mod
    32.25
    (mod
    32.00
     modulation
    31.38
    MOD
    29.00
    Activations Density 0.019%

    No Known Activations