© 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. 15530
    Prev
    Next
    INDEX
    Explanations

    say vision

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

    No Comments

    Negative Logits
    azer
    -17.50
    ��
    -16.38
    omal
    -16.25
     jackpot
    -16.13
     quart
    -16.13
    mites
    -16.00
     nickel
    -15.38
    车祸
    -14.75
    Hz
    -14.63
    仪式
    -14.56
    POSITIVE LOGITS
     vision
    22.50
     message
    20.25
     messages
    19.75
     Strand
    19.38
     messaging
    18.88
    メッセージ
    18.75
    :message
    18.38
     Vision
    18.13
    Vision
    18.00
    SendMessage
    17.75
    Activations Density 0.234%

    No Known Activations