© 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. 16177
    Prev
    Next
    INDEX
    Explanations

    mens rea

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

    No Comments

    Negative Logits
    PEG
    -19.75
     TRACK
    -19.25
    afia
    -19.00
    $header
    -18.25
    _track
    -18.00
    _TRACK
    -18.00
    Tracking
    -17.88
     tracking
    -17.88
    ropy
    -17.38
    洙
    -17.13
    POSITIVE LOGITS
     integr
    17.13
    -int
    15.81
    itsu
    15.13
    tsx
    15.00
     integral
    15.00
     volunt
    14.75
    故意
    14.75
     mens
    14.75
    integr
    14.75
     unlaw
    14.44
    Activations Density 0.085%

    No Known Activations