© 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. 15842
    Prev
    Next
    INDEX
    Explanations

    say non‑ASCII characters

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

    No Comments

    Negative Logits
     alph
    -21.00
    alse
    -19.38
    Sec
    -18.38
    alph
    -18.25
    -de
    -18.00
     alpha
    -17.88
     Sec
    -17.88
    Alpha
    -17.75
     alphabet
    -17.50
    脱
    -17.38
    POSITIVE LOGITS
    ocol
    20.13
    勐
    18.50
     Shade
    18.25
     plage
    17.88
     Cold
    17.75
    冷
    17.13
    Cold
    17.00
    péri
    17.00
     shock
    17.00
    osh
    16.88
    Activations Density 3.437%

    No Known Activations