© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2912
    Prev
    Next
    INDEX
    Explanations

    say inc

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

    No Comments

    Negative Logits
     semantics
    -19.13
    终端
    -16.00
    gens
    -15.81
    _terminal
    -15.56
    _strategy
    -15.50
     generics
    -15.38
    cock
    -15.19
     republic
    -15.19
    strategy
    -14.94
    _deriv
    -14.88
    POSITIVE LOGITS
     Inc
    63.00
    Inc
    62.00
     incident
    54.25
     inc
    54.00
    inc
    51.00
    _inc
    49.00
     incidence
    46.00
    -inc
    44.50
    .inc
    44.00
    incident
    44.00
    Activations Density 0.185%

    No Known Activations