© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15256
    Prev
    Next
    INDEX
    Explanations

    say emotion words

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

    No Comments

    Negative Logits
    	play
    -18.75
     stepper
    -18.38
     playerName
    -17.88
    resolve
    -17.88
     ticket
    -17.75
     playerId
    -17.63
     playable
    -17.50
     audition
    -17.38
     player
    -17.25
    ASSERT
    -17.25
    POSITIVE LOGITS
    -generator
    18.00
    服务
    17.88
     GENER
    17.63
     generated
    17.25
     genera
    17.00
     service
    16.88
    生成
    16.75
     generation
    16.50
     generating
    16.13
    -generated
    16.00
    Activations Density 0.184%

    No Known Activations