© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    any => eth

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

    No Comments

    Negative Logits
     Hess
    -20.00
    hn
    -19.50
    inn
    -18.63
    inas
    -18.63
    Inset
    -18.38
    ím
    -18.00
    ina
    -17.63
    inois
    -17.38
    inan
    -17.38
    ine
    -17.13
    POSITIVE LOGITS
    obic
    20.25
    pare
    17.88
     Sik
    17.50
    braco
    17.25
    avic
    17.13
    acie
    17.00
    paren
    16.63
     VIC
    16.50
    修理
    16.38
     Suffolk
    16.00
    Activations Density 0.570%

    No Known Activations