© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14602
    Prev
    Next
    INDEX
    Explanations

    say binary

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

    No Comments

    Negative Logits
    塞
    -16.75
    垫
    -15.06
    震荡
    -14.63
    堵塞
    -14.31
    oro
    -14.00
    �
    -14.00
    2
    -13.25
    1
    -13.00
    \Collection
    -12.88
    庞
    -12.81
    POSITIVE LOGITS
     Jah
    22.75
    htable
    21.50
     Bihar
    20.75
    ihu
    19.88
     Fah
    19.88
     Jeh
    19.63
     hx
    19.50
    dfa
    19.38
    hot
    18.88
    神州
    18.50
    Activations Density 0.109%

    No Known Activations