© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    say "hex digits"

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

    No Comments

    Negative Logits
    -d
    -21.00
    D
    -19.88
    d
    -19.88
    _d
    -19.38
     D
    -19.13
    ДЕ
    -19.00
     d
    -18.75
    idar
    -18.75
    )d
    -17.63
    indh
    -17.63
    POSITIVE LOGITS
    apas
    19.50
    atum
    17.75
    aku
    17.50
    ağı
    17.38
    ап
    17.38
    aa
    17.38
    aqu
    17.13
    kap
    16.75
     appe
    16.63
    Assembly
    16.63
    Activations Density 0.512%

    No Known Activations