© 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. 2628
    Prev
    Next
    INDEX
    Explanations

    municipal

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

    No Comments

    Negative Logits
    范
    -25.38
     rec
    -21.00
     er
    -20.88
     dem
    -18.38
     rem
    -18.13
     Er
    -17.88
    万
    -16.50
     rad
    -16.25
     quant
    -16.25
    (obj
    -16.13
    POSITIVE LOGITS
    市政
    21.50
    emit
    20.13
     Benz
    19.38
     SEM
    18.50
     Emil
    18.25
     benz
    17.63
    Mur
    17.13
    Digest
    17.13
    esz
    16.88
    苯
    16.63
    Activations Density 0.086%

    No Known Activations