© 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. 14720
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    塑
    -16.88
    嗓
    -15.88
     reels
    -14.75
    冉
    -14.56
    射
    -14.50
    ucc
    -14.31
    叙事
    -14.13
    农牧
    -14.00
    邋
    -13.69
     rex
    -13.63
    POSITIVE LOGITS
     Central
    16.63
    ebin
    16.25
    dia
    15.88
    lashes
    15.38
    ods
    15.19
    .baidu
    15.13
    lags
    14.94
    Agents
    14.94
    di
    14.81
    (di
    14.81
    Activations Density 0.579%

    No Known Activations