© 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. 15258
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     cud
    -19.50
    趸
    -19.00
     Freder
    -18.88
    瀼
    -18.75
     Bing
    -18.25
    IDD
    -18.00
    erno
    -18.00
    ibus
    -17.88
    ritt
    -17.75
     Huck
    -17.75
    POSITIVE LOGITS
    alth
    16.50
    劣
    14.56
    �
    14.13
    otre
    13.75
    be
    13.13
    y
    12.88
    com
    12.81
    care
    12.50
    holds
    12.31
    莜
    12.25
    Activations Density 0.050%

    No Known Activations