© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16093
    Prev
    Next
    INDEX
    Explanations

    [ood] => [Osgood]

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

    No Comments

    Negative Logits
    .decorate
    -20.50
    氡
    -17.63
     jade
    -17.38
    (dc
    -16.75
    芳香
    -16.63
    .Gradient
    -16.50
    decorate
    -16.38
    ATTR
    -16.38
    胧
    -16.25
    Decor
    -16.13
    POSITIVE LOGITS
     Plate
    19.63
     plate
    19.00
    �
    18.88
     plates
    18.38
     Pro
    18.38
    rei
    18.00
    _PRO
    17.88
    -Pro
    17.75
     plat
    17.63
    .pro
    17.38
    Activations Density 1.104%

    No Known Activations