© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15571
    Prev
    Next
    INDEX
    Explanations

    say "automatic"

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

    No Comments

    Negative Logits
    旗
    -17.63
    goal
    -16.50
    山顶
    -16.38
    goals
    -16.00
    Peak
    -15.94
    ManagerInterface
    -15.88
    _spaces
    -15.81
    Marvel
    -15.81
    VERTEX
    -15.31
    高空
    -15.31
    POSITIVE LOGITS
    胚胎
    19.13
    生物
    18.25
     autom
    18.25
    自動
    17.50
     ingr
    17.00
     embryos
    17.00
    _imm
    16.63
    養
    16.38
     automat
    16.25
    プログラム
    16.13
    Activations Density 0.317%

    No Known Activations