© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16046
    Prev
    Next
    INDEX
    Explanations

    middle

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

    No Comments

    Negative Logits
     gris
    -17.38
    .gms
    -16.00
     Guarantee
    -15.44
    中枢
    -15.44
    opi
    -15.31
     Emil
    -14.88
    .github
    -14.88
    Hu
    -14.75
    positories
    -14.56
    抗菌
    -14.44
    POSITIVE LOGITS
    erate
    17.25
    iele
    16.00
    adden
    15.75
     RTE
    15.25
    (att
    15.13
    oad
    15.00
    ranges
    14.81
     att
    14.81
    IEL
    14.75
    orge
    14.63
    Activations Density 0.030%

    No Known Activations