© 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. 14855
    Prev
    Next
    INDEX
    Explanations

    parenthesized numbers

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

    No Comments

    Negative Logits
     hed
    -17.50
    HAM
    -16.50
    _sha
    -16.13
     hammer
    -15.81
    (Fl
    -15.25
     Hammer
    -15.19
    ettes
    -15.06
    Jam
    -15.00
     Flo
    -14.94
    amble
    -14.94
    POSITIVE LOGITS
    spath
    19.13
    azar
    18.25
    apg
    18.00
    atak
    17.88
    irk
    17.25
     Пар
    17.13
     mongoose
    17.00
    izards
    17.00
    orz
    16.88
    anoi
    16.88
    Activations Density 0.854%

    No Known Activations