© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1342
    Prev
    Next
    INDEX
    Explanations

    alphabetical order

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

    No Comments

    Negative Logits
    字母
    -32.50
     alph
    -30.75
     alphabet
    -30.25
     alpha
    -27.63
    alphabet
    -27.25
    alpha
    -26.88
    Alpha
    -26.75
     Alpha
    -25.25
     Alphabet
    -25.00
    .alpha
    -24.88
    POSITIVE LOGITS
     policy
    21.00
     policies
    19.25
    _media
    18.50
    政策
    18.13
    policy
    17.63
     Policy
    17.50
    媒体
    16.50
     media
    16.38
    media
    16.25
    Policy
    16.25
    Activations Density 0.051%

    No Known Activations