© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 404
    Prev
    Next
    INDEX
    Explanations

    [become] => [active]

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

    No Comments

    Negative Logits
     surgeon
    -20.75
    血管
    -20.63
    獸
    -19.25
    泌
    -18.25
     surgical
    -18.00
     surgery
    -17.88
    兽
    -17.75
    门诊
    -17.13
    手术
    -17.13
     surgeons
    -17.13
    POSITIVE LOGITS
    ilver
    19.13
     tb
    15.69
     rb
    15.19
    Ir
    15.00
     rs
    14.81
    irl
    14.81
    Cd
    14.75
    mx
    14.69
     cid
    14.63
     ga
    14.56
    Activations Density 0.303%

    No Known Activations