© 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. 14306
    Prev
    Next
    INDEX
    Explanations

    say "listen"

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

    No Comments

    Negative Logits
    Push
    -19.25
     Push
    -18.38
    开通
    -18.00
     push
    -17.88
    压
    -17.75
    壓
    -17.75
     PUSH
    -17.63
    push
    -17.50
    -push
    -17.50
     pushing
    -17.38
    POSITIVE LOGITS
    _assoc
    17.75
     listeners
    16.13
    组合
    15.63
     listener
    15.56
     listen
    15.56
     Listener
    15.25
    执行
    15.25
     bound
    14.88
    cis
    14.81
    组成
    14.81
    Activations Density 3.479%

    No Known Activations