© 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. 15356
    Prev
    Next
    INDEX
    Explanations

    say "4"

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

    No Comments

    Negative Logits
    燧
    -21.75
    �
    -19.38
    _CSR
    -19.38
    _oid
    -18.75
    rella
    -18.63
    taire
    -18.50
    ahir
    -18.38
     Campbell
    -18.38
    csr
    -18.38
    sitemap
    -18.25
    POSITIVE LOGITS
    iges
    17.25
    诛
    16.38
    lobal
    15.69
    lass
    15.44
    ubes
    15.31
     abb
    15.25
    ub
    14.81
    قب
    14.81
    pieces
    14.50
    Jessica
    14.38
    Activations Density 0.126%

    No Known Activations