© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1327
    Prev
    Next
    INDEX
    Explanations

    do not say ion

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

    No Comments

    Negative Logits
     ion
    -40.25
     Ion
    -39.25
    Ion
    -38.50
    离子
    -38.25
     ions
    -36.75
    -ion
    -36.25
    /ion
    -33.50
     io
    -32.50
    ION
    -31.13
    ion
    -29.00
    POSITIVE LOGITS
    ubuntu
    16.63
    ertext
    14.69
     Chester
    14.25
    Books
    13.88
     GNU
    13.75
    lambda
    13.63
    -books
    13.63
    -book
    13.50
    Book
    13.44
     Essex
    13.44
    Activations Density 0.103%

    No Known Activations