© 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. 14377
    Prev
    Next
    INDEX
    Explanations

    in

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

    No Comments

    Negative Logits
    e
    -18.00
    a
    -15.94
    str
    -14.50
    eh
    -14.50
    排除
    -14.19
    ea
    -13.75
    uten
    -13.56
    utable
    -13.50
    ural
    -13.31
    eda
    -13.06
    POSITIVE LOGITS
     Clint
    20.50
    缢
    19.75
     Creek
    19.25
     Cliff
    19.13
     Jug
    18.13
     crib
    17.88
     Dixon
    17.63
    アジア
    17.13
    呻
    17.13
     Cyc
    17.00
    Activations Density 0.377%

    No Known Activations