© 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. 14894
    Prev
    Next
    INDEX
    Explanations

    say "9"

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

    No Comments

    Negative Logits
    wig
    -17.75
     Bang
    -17.38
    BF
    -16.88
    SWG
    -16.38
     SF
    -16.13
    igy
    -15.88
    _sf
    -15.50
    +")
    -15.31
     BF
    -15.25
    帝王
    -15.13
    POSITIVE LOGITS
    noon
    21.00
    ollen
    19.25
    rolled
    19.25
    mutations
    18.25
    mutation
    17.63
    ooled
    17.38
    ción
    17.13
    uncia
    17.13
    utes
    17.00
    elsen
    16.88
    Activations Density 0.019%

    No Known Activations