© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16283
    Prev
    Next
    INDEX
    Explanations

    say "audio"

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

    No Comments

    Negative Logits
    钢板
    -19.88
    .addView
    -19.00
    管委会
    -18.13
    视力
    -17.75
    Vision
    -17.50
     elbow
    -17.00
    沧州
    -17.00
    visibility
    -16.50
    vision
    -16.38
     Benghazi
    -16.38
    POSITIVE LOGITS
     audio
    30.50
     sound
    30.00
     Audio
    29.88
    音频
    29.25
    (Audio
    29.25
    	audio
    28.63
    sound
    28.38
    Sound
    28.25
     AUDIO
    28.00
     AudioSource
    28.00
    Activations Density 0.132%

    No Known Activations