© 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. 14833
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    wall
    -18.38
    ellt
    -16.88
    ansen
    -16.25
    ensus
    -16.00
    encion
    -15.81
    Wall
    -15.75
    mont
    -15.56
    gend
    -15.50
    usterity
    -15.13
    熵
    -15.00
    POSITIVE LOGITS
    6
    25.13
    8
    21.50
    7
    21.50
    ６
    20.75
     six
    20.50
    9
    19.50
     eight
    18.63
    six
    18.63
    ８
    18.38
    -six
    18.13
    Activations Density 0.012%

    No Known Activations