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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1101
    Prev
    Next
    INDEX
    Explanations

    say innov

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

    No Comments

    Negative Logits
     Beach
    -22.38
    _beam
    -21.00
     beaches
    -21.00
     beach
    -20.25
     beam
    -20.13
     beer
    -19.88
     Beer
    -19.25
     beams
    -19.13
    梁
    -18.75
     Book
    -18.25
    POSITIVE LOGITS
     innovation
    20.50
    盐
    20.25
     python
    19.00
    创新
    18.88
     Python
    18.63
     innovate
    18.50
     innovative
    18.38
     Innovative
    17.38
     salt
    17.13
     innov
    17.00
    Activations Density 0.223%

    No Known Activations