© 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. 16018
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII tokens

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

    No Comments

    Negative Logits
     spill
    -25.13
     Sp
    -24.00
    Sp
    -23.25
    _sp
    -23.25
    .sp
    -23.13
    sp
    -22.75
    -sp
    -22.38
    /sp
    -22.25
    osp
    -20.88
    .Sp
    -20.75
    POSITIVE LOGITS
     Alexand
    17.88
     sher
    16.75
    侠
    16.63
    /bind
    15.94
    hel
    15.94
     quaternion
    15.44
     Quaternion
    15.31
    sher
    15.25
     plat
    15.13
    _op
    15.06
    Activations Density 0.678%

    No Known Activations