© 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. 14753
    Prev
    Next
    INDEX
    Explanations

    Fact

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

    No Comments

    Negative Logits
    nego
    -13.88
    phia
    -13.75
    zia
    -13.44
    ffffff
    -13.44
    breadcrumbs
    -13.13
     RATE
    -13.06
    cura
    -12.94
     blush
    -12.94
     humid
    -12.94
    nda
    -12.88
    POSITIVE LOGITS
    imming
    14.81
    _raise
    14.38
    ительн
    13.81
    strup
    13.69
     Enemy
    13.50
    enames
    13.50
    izador
    13.44
     raising
    13.38
    抉
    13.31
    ":"","
    13.13
    Activations Density 0.156%

    No Known Activations