© 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. 14247
    Prev
    Next
    INDEX
    Explanations

    say radio

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

    No Comments

    Negative Logits
     Eval
    -17.88
    评价
    -16.88
    pute
    -16.63
     Evalu
    -16.63
    VisualStyle
    -16.50
     evaluator
    -16.13
     EVAL
    -16.00
    投保
    -16.00
    产销
    -15.94
    REATE
    -15.81
    POSITIVE LOGITS
     radio
    36.50
     broadcast
    34.50
    广播
    34.25
     broadcasts
    33.75
     Radio
    31.75
    broadcast
    31.13
     broadcasting
    30.50
    无线电
    30.50
     Broadcast
    30.38
    Broadcast
    30.38
    Activations Density 0.479%

    No Known Activations