© 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. 2767
    Prev
    Next
    INDEX
    Explanations

    say "techn" words

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

    No Comments

    Negative Logits
     architecture
    -17.00
    architecture
    -16.88
    Architecture
    -16.00
    hei
    -15.81
     Caps
    -15.31
     mathematics
    -15.13
    ittal
    -15.06
    内存
    -14.75
     Architecture
    -14.75
    MEM
    -14.63
    POSITIVE LOGITS
     Techn
    45.75
    Techn
    41.00
     techn
    40.25
    科技
    38.25
     technological
    36.50
    techn
    35.75
     Tech
    33.75
     tech
    33.00
    Tech
    31.25
    技
    29.88
    Activations Density 0.061%

    No Known Activations