© 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. 15601
    Prev
    Next
    INDEX
    Explanations

    author names

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

    No Comments

    Negative Logits
    -n
    -47.50
    ナ
    -42.50
    nu
    -42.00
    nit
    -42.00
    尼
    -41.50
    ネ
    -41.25
    na
    -40.25
    nic
    -40.00
     nap
    -39.75
    nn
    -39.50
    POSITIVE LOGITS
    偓
    14.56
    dex
    13.00
    phalt
    12.88
    ilingual
    12.50
     Hancock
    12.44
    olkien
    12.19
    枯燥
    12.00
     ча
    11.94
    戗
    11.94
    苌
    11.94
    Activations Density 3.354%

    No Known Activations