© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14604
    Prev
    Next
    INDEX
    Explanations

    say miles

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

    No Comments

    Negative Logits
    orias
    -19.13
    oom
    -18.75
    oa
    -18.63
    OOM
    -18.25
    iale
    -18.13
    iali
    -17.50
    "url
    -17.50
    ialis
    -17.25
     IDisposable
    -17.13
    筹码
    -17.00
    POSITIVE LOGITS
    蚊
    15.75
    水上
    15.00
     Brent
    15.00
     Sapphire
    14.13
     bomber
    14.06
    浦
    13.81
    pped
    13.56
     Cong
    13.56
    Fant
    13.50
    卓
    12.94
    Activations Density 0.047%

    No Known Activations