© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14671
    Prev
    Next
    INDEX
    Explanations

    say "1"

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

    No Comments

    Negative Logits
     Riley
    -19.25
     Tanz
    -18.63
     LDS
    -17.63
     TCL
    -17.25
    chl
    -17.25
    enal
    -17.13
    senal
    -17.13
    HAL
    -16.88
     Rachel
    -16.88
    ahlen
    -16.63
    POSITIVE LOGITS
    robe
    18.00
    avax
    17.38
    oge
    17.25
    pery
    16.75
    Ice
    16.50
     Ice
    16.50
     icing
    16.13
    ROTO
    16.00
    ices
    15.94
    rots
    15.81
    Activations Density 0.090%

    No Known Activations