© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    say "listening"

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

    No Comments

    Negative Logits
    絜
    -19.75
    visibility
    -18.13
     Proposal
    -16.38
    bilt
    -15.75
    搦
    -15.63
    licht
    -15.56
    Proposal
    -15.50
     симв
    -15.44
     symbolism
    -15.31
     Vect
    -15.25
    POSITIVE LOGITS
     listening
    55.50
     listener
    54.25
     listen
    53.50
     listeners
    52.00
    听
    51.50
    监听
    50.75
     Listener
    50.75
     Listening
    50.50
    听众
    50.25
     hearing
    49.75
    Activations Density 0.369%

    No Known Activations