© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15762
    Prev
    Next
    INDEX
    Explanations

    say "binary"

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

    No Comments

    Negative Logits
    APH
    -19.63
    均价
    -18.25
    保费
    -17.00
    ホーム
    -17.00
    coach
    -16.25
    _SPR
    -16.13
     MVP
    -16.00
     authDomain
    -15.38
    phia
    -15.31
    jee
    -15.25
    POSITIVE LOGITS
     binary
    30.50
    Binary
    29.50
     Binary
    29.00
     bits
    27.75
    bit
    27.75
     Bits
    27.00
    比特
    26.75
     bit
    26.50
    binary
    26.25
    /bit
    26.25
    Activations Density 0.128%

    No Known Activations