© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    say experts

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

    No Comments

    Negative Logits
    -insert
    -18.75
     حص
    -15.81
     Samples
    -15.69
    填
    -15.50
     Guerr
    -15.38
    -price
    -15.31
    adds
    -15.25
    凫
    -15.19
    新娘
    -15.19
    .entries
    -15.19
    POSITIVE LOGITS
    OPT
    15.31
     intelig
    14.75
    -opt
    14.63
     intellig
    14.50
     acad
    14.50
     Grove
    14.38
    ograd
    14.25
     academic
    14.06
    智能
    13.69
     comment
    13.56
    Activations Density 0.153%

    No Known Activations