© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    say "ern"

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

    No Comments

    Negative Logits
    _seg
    -21.50
    Seg
    -21.50
     seg
    -21.00
    leg
    -19.00
     Seg
    -18.75
    proposal
    -18.50
    Segment
    -18.38
    	util
    -18.25
    (segment
    -17.88
    (cn
    -17.75
    POSITIVE LOGITS
     bin
    20.38
     sen
    20.25
    den
    20.25
     den
    20.00
     len
    19.75
    (len
    18.63
     Sen
    18.25
     Den
    17.88
    len
    17.75
    =len
    17.63
    Activations Density 0.165%

    No Known Activations