© 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. 15570
    Prev
    Next
    INDEX
    Explanations

    say "heat"

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

    No Comments

    Negative Logits
    -par
    -19.75
    狸
    -19.25
    _par
    -19.00
     fantasy
    -18.75
    Par
    -17.88
    Fant
    -17.38
     Suk
    -17.38
    riel
    -17.25
    Guy
    -17.25
     suk
    -17.13
    POSITIVE LOGITS
    煅
    18.88
     Digest
    18.25
    熨
    17.88
    消化
    17.38
    �
    17.00
     flare
    16.88
    灼
    16.88
    _Red
    16.00
    earing
    16.00
    digest
    15.81
    Activations Density 1.065%

    No Known Activations