© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15800
    Prev
    Next
    INDEX
    Explanations

    say verbs

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

    No Comments

    Negative Logits
    éri
    -18.75
     antiqu
    -17.75
    MARY
    -17.63
     mystical
    -17.63
    _ant
    -17.50
    วร
    -17.25
    嫉妒
    -17.25
    LECT
    -17.00
     kj
    -16.88
    sonian
    -16.75
    POSITIVE LOGITS
    lassian
    16.50
     Corvette
    16.38
     dashboard
    15.69
     Dodd
    15.25
     beef
    15.19
    usted
    15.13
     grease
    14.63
     Chevrolet
    14.50
    tested
    14.25
     fleets
    14.13
    Activations Density 0.469%

    No Known Activations