© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15058
    Prev
    Next
    INDEX
    Explanations

    say acronyms

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

    No Comments

    Negative Logits
    am
    -29.00
    amm
    -28.13
    em
    -27.00
    emm
    -26.38
    äm
    -25.50
    ammo
    -24.63
     Emm
    -24.63
    amation
    -24.38
    ам
    -24.13
    ém
    -24.00
    POSITIVE LOGITS
     prof
    15.00
     defensively
    14.50
    迤
    14.38
     scn
    13.94
    dı
    13.69
    ít
    13.44
    NING
    13.13
    哲
    13.06
    AGED
    12.56
    ningar
    12.56
    Activations Density 0.215%

    No Known Activations