© 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. 14938
    Prev
    Next
    INDEX
    Explanations

    say "O"

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

    No Comments

    Negative Logits
    O
    -39.50
     O
    -36.50
     o
    -35.00
    -o
    -34.00
    o
    -33.25
    奥
    -32.25
    奧
    -30.38
    	o
    -30.13
    -O
    -30.13
    _o
    -30.00
    POSITIVE LOGITS
    endi
    16.25
    enn
    14.88
    ensi
    14.75
    渚
    14.56
    adders
    14.56
    �
    13.63
    atalog
    13.63
    滋养
    13.56
    车道
    13.50
    ény
    13.44
    Activations Density 1.012%

    No Known Activations