© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15567
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    Spider
    -19.50
    miner
    -19.25
     Spider
    -18.75
    acz
    -18.38
    玉石
    -18.25
     Mormons
    -18.00
    清水
    -17.38
     depleted
    -17.25
     Spokane
    -17.00
    石榴
    -17.00
    POSITIVE LOGITS
    rouw
    17.50
    握手
    16.75
    alle
    16.13
    嗳
    16.00
     Axel
    15.88
    _co
    15.81
     typealias
    15.63
     plat
    15.56
    -co
    15.44
    ersen
    15.31
    Activations Density 1.647%

    No Known Activations