© 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. 15084
    Prev
    Next
    INDEX
    Explanations

    say "6"

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

    No Comments

    Negative Logits
    睢
    -26.00
    桂
    -23.88
    avic
    -21.00
    舸
    -19.75
    Gab
    -19.50
    vue
    -19.13
     Cabr
    -19.00
    iese
    -19.00
    icare
    -18.75
    ague
    -18.63
    POSITIVE LOGITS
     Jennifer
    19.63
    Jennifer
    18.25
     Jenn
    17.50
    jit
    16.13
     choke
    16.00
     choking
    15.19
     Jurassic
    15.13
    疗
    15.06
     Palin
    15.00
     Jenny
    14.81
    Activations Density 0.099%

    No Known Activations