© 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. 15885
    Prev
    Next
    INDEX
    Explanations

    say gradient

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

    No Comments

    Negative Logits
    exus
    -19.63
    ebx
    -18.13
    ieten
    -18.00
     Cristina
    -17.50
    iei
    -17.38
    iban
    -17.25
     Assassin
    -17.25
    捕鱼
    -17.00
    fi
    -17.00
     ebx
    -16.88
    POSITIVE LOGITS
    gradient
    20.38
     gradient
    20.25
    GRA
    19.00
     gradients
    18.13
    pike
    18.00
    _grad
    18.00
    Gradient
    17.75
     graded
    17.75
    _GRA
    17.50
    gra
    17.38
    Activations Density 0.030%

    No Known Activations