© 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. 14772
    Prev
    Next
    INDEX
    Explanations

    say "subword continuation"

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

    No Comments

    Negative Logits
     di
    -27.50
    dí
    -21.25
     Di
    -21.25
     Nap
    -21.00
    di
    -21.00
    Di
    -20.50
    -di
    -20.13
    _di
    -19.75
    섭
    -19.63
    .di
    -19.00
    POSITIVE LOGITS
    imore
    17.75
     Patterson
    15.25
    _secure
    14.94
    _gshared
    14.94
    INGER
    14.44
    apl
    14.06
    rench
    13.75
     ugl
    13.75
     shred
    13.13
    璋
    13.13
    Activations Density 0.432%

    No Known Activations