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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16049
    Prev
    Next
    INDEX
    Explanations

    say "F combos"

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

    No Comments

    Negative Logits
    噜
    -14.94
    ąc
    -12.69
    楯
    -12.50
    梧
    -12.44
    戟
    -12.13
    MatrixXd
    -12.06
    瓒
    -12.00
     dáng
    -11.88
     Rut
    -11.75
    乌鲁
    -11.75
    POSITIVE LOGITS
    -f
    43.50
    fc
    43.50
    fs
    42.00
    	ff
    41.25
    fi
    41.25
    fm
    41.00
    FF
    40.00
     fc
    39.50
    FA
    39.25
    FC
    39.25
    Activations Density 8.710%

    No Known Activations