© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15124
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    arie
    -20.88
    便利店
    -20.13
    anko
    -19.63
    樗
    -19.50
    mtree
    -18.50
    lein
    -18.13
     Onion
    -17.88
     Babe
    -17.63
     ballo
    -17.63
    oload
    -17.50
    POSITIVE LOGITS
     fest
    13.44
    فات
    13.19
    ˈ
    13.00
    elter
    12.94
    -ren
    12.81
    hal
    12.69
     progn
    12.38
    F
    12.19
    2
    12.19
     Fel
    12.00
    Activations Density 0.058%

    No Known Activations