© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    say conservation

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

    No Comments

    Negative Logits
     digit
    -18.00
    utch
    -17.50
    hex
    -17.38
    (mut
    -17.13
     Jer
    -17.00
    数字化
    -16.63
    ourt
    -16.50
     digitally
    -16.50
    胚
    -16.13
     digits
    -15.75
    POSITIVE LOGITS
    Cons
    63.75
     conservation
    63.50
    cons
    62.50
     conserv
    62.00
     Conservation
    59.50
     Conserv
    55.75
    -cons
    55.50
     conserve
    54.50
     cons
    53.25
     Cons
    52.25
    Activations Density 0.176%

    No Known Activations