© 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. 15505
    Prev
    Next
    INDEX
    Explanations

    [number] => [degrees]

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

    No Comments

    Negative Logits
    �
    -18.13
     Trev
    -17.25
    mitted
    -17.25
    肟
    -15.94
    ira
    -15.81
    terra
    -15.56
     TNT
    -15.50
    argon
    -15.44
    qn
    -15.25
     Cass
    -15.19
    POSITIVE LOGITS
     degrees
    32.50
    degrees
    30.75
    Deg
    30.63
    Degrees
    29.63
     Degrees
    29.50
     Deg
    28.88
    _deg
    28.75
     degree
    28.50
    -degree
    28.38
    _degree
    28.25
    Activations Density 0.061%

    No Known Activations