© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15609
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    dap
    -19.63
    rok
    -19.50
    .ny
    -18.38
     zro
    -18.38
    Prov
    -17.75
     Troy
    -17.38
    萘
    -17.25
     rz
    -17.13
     Nev
    -17.00
    zk
    -17.00
    POSITIVE LOGITS
    illator
    18.63
    Paginator
    17.13
    斛
    16.88
    illa
    16.75
    stra
    16.50
    paginator
    16.13
    .charCodeAt
    16.00
     �
    15.88
    ilda
    15.81
    ill
    15.75
    Activations Density 0.138%

    No Known Activations