© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    say "ev"

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

    No Comments

    Negative Logits
    =res
    -19.75
    (res
    -19.63
     merit
    -18.88
     Mer
    -18.75
    位
    -18.75
    Cur
    -18.00
     mer
    -18.00
    _cur
    -17.88
     resin
    -17.63
     Tem
    -17.50
    POSITIVE LOGITS
    Ev
    43.75
     ev
    41.75
    ev
    40.75
    -ev
    40.25
    	ev
    39.50
     EV
    39.25
     Evangel
    39.00
     Ev
    38.75
     evolutionary
    38.00
    _ev
    37.00
    Activations Density 0.024%

    No Known Activations