© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    say "cross"

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

    No Comments

    Negative Logits
    inals
    -19.88
     babel
    -17.13
    lemen
    -16.63
    ément
    -16.63
    	writer
    -16.50
    inking
    -16.50
    書き
    -16.38
    NOP
    -16.25
    fst
    -16.25
    fight
    -16.25
    POSITIVE LOGITS
     cross
    14.56
     Haut
    14.06
    .cross
    13.94
    顷
    13.81
     Cross
    13.44
     valign
    12.69
    <!--[
    12.69
    _HIDE
    12.63
    _cross
    12.63
     Images
    12.63
    Activations Density 0.110%

    No Known Activations