© 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. 15147
    Prev
    Next
    INDEX
    Explanations

    say digit

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

    No Comments

    Negative Logits
    出场
    -16.13
    埭
    -15.81
    到账
    -15.69
    ifest
    -14.81
    ummer
    -14.81
    owered
    -14.63
    ptype
    -14.63
    éro
    -14.38
    薪水
    -14.31
    BaseContext
    -13.94
    POSITIVE LOGITS
     Peninsula
    15.06
     square
    14.69
    bits
    14.56
     thơ
    14.44
     peninsula
    14.38
     squares
    14.00
    onyms
    13.81
     areas
    13.69
    全县
    13.63
     Areas
    13.56
    Activations Density 0.027%

    No Known Activations