© 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. 2567
    Prev
    Next
    INDEX
    Explanations

    say "sem"

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

    No Comments

    Negative Logits
    	iter
    -16.88
    -multi
    -16.13
     req
    -15.94
    Multi
    -15.13
     multi
    -15.06
     validators
    -14.94
    habi
    -14.88
    (iter
    -14.88
    hat
    -14.81
    (req
    -14.75
    POSITIVE LOGITS
     sem
    87.50
     Sem
    83.50
    Sem
    83.00
    sem
    79.50
    _sem
    74.00
    (sem
    72.00
    -sem
    70.50
    .sem
    68.50
    	sem
    68.00
     SEM
    61.50
    Activations Density 0.197%

    No Known Activations