© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1801
    Prev
    Next
    INDEX
    Explanations

    do not say cell

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

    No Comments

    Negative Logits
     cellular
    -27.13
     Cellular
    -24.38
    细胞
    -22.38
    _cell
    -22.25
    CELL
    -22.13
     TableCell
    -22.00
    cell
    -21.75
     cell
    -21.75
    _Cell
    -21.75
     cells
    -21.63
    POSITIVE LOGITS
     arch
    18.75
     fian
    17.63
    光
    17.50
     amazon
    15.88
     Pdf
    15.69
     Amazon
    15.44
     psychology
    15.38
     Arch
    15.25
     Di
    15.13
     magic
    15.06
    Activations Density 0.137%

    No Known Activations