© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2139
    Prev
    Next
    INDEX
    Explanations

    say compounds

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

    No Comments

    Negative Logits
    眼球
    -16.25
    akedown
    -16.13
    acus
    -15.94
     fractures
    -15.88
     fracture
    -15.44
    .overflow
    -15.44
     EM
    -15.38
    _SEG
    -15.25
    籴
    -15.13
    Gem
    -15.00
    POSITIVE LOGITS
    化合物
    22.88
    萜
    20.13
     compounds
    19.88
     flav
    19.88
    农药
    18.25
    compound
    18.13
    植物
    17.88
     Compound
    17.00
    anol
    17.00
     compound
    17.00
    Activations Density 0.122%

    No Known Activations