© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14910
    Prev
    Next
    INDEX
    Explanations

    say 2

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

    No Comments

    Negative Logits
    雉
    -19.75
     Scala
    -19.75
     Raleigh
    -19.00
    scanner
    -18.50
     haystack
    -18.13
    scala
    -18.00
     Drake
    -18.00
     Reaper
    -17.88
     maple
    -17.75
    杉
    -17.75
    POSITIVE LOGITS
    _gem
    16.00
    团
    15.25
    horn
    15.00
     �
    14.81
     cry
    14.25
    orie
    14.06
    town
    13.63
    OLID
    13.50
    ARM
    13.44
    EW
    13.44
    Activations Density 0.057%

    No Known Activations