© 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. 14555
    Prev
    Next
    INDEX
    Explanations

    say "original"

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

    No Comments

    Negative Logits
    conv
    -18.25
    bfd
    -18.00
    protein
    -17.50
    iffe
    -17.38
    asn
    -17.00
    iste
    -16.88
    _conv
    -16.75
     conv
    -16.75
    isten
    -16.25
    发酵
    -16.13
    POSITIVE LOGITS
    dic
    16.88
    di
    16.75
    oric
    16.38
    源泉
    15.88
     di
    15.63
     Diy
    15.38
    oku
    15.19
    OTH
    14.69
    _dic
    14.50
    dj
    14.50
    Activations Density 0.508%

    No Known Activations