© 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. 14745
    Prev
    Next
    INDEX
    Explanations

    say "6"

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

    No Comments

    Negative Logits
    etti
    -17.75
    �
    -17.13
    icycle
    -16.75
     relic
    -16.63
     Willis
    -16.63
    婊
    -16.25
    死了
    -16.00
    ialis
    -16.00
    奥巴马
    -15.88
     Fare
    -15.75
    POSITIVE LOGITS
    ln
    15.94
     oud
    14.88
    ogi
    13.81
     Meghan
    13.44
    -md
    13.31
    ou
    13.13
    Ing
    12.88
    суд
    12.88
    avn
    12.88
     partial
    12.75
    Activations Density 0.005%

    No Known Activations