© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14183
    Prev
    Next
    INDEX
    Explanations

    say "calculation"

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

    No Comments

    Negative Logits
    ObjectType
    -18.00
    ObjectName
    -16.75
    autiful
    -15.69
    CATEGORY
    -15.50
     anthology
    -15.31
     skills
    -15.25
     creations
    -15.13
     organización
    -14.94
     organization
    -14.94
     collect
    -14.81
    POSITIVE LOGITS
    计算
    72.50
     calculation
    64.00
    計算
    61.50
    calc
    61.25
    Calc
    59.75
     Calcul
    59.50
    (calc
    58.50
     calculations
    58.25
     calcul
    58.00
     calc
    57.75
    Activations Density 1.347%

    No Known Activations