© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16209
    Prev
    Next
    INDEX
    Explanations

    say deep

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

    No Comments

    Negative Logits
    ProcessEvent
    -20.50
    ListModel
    -18.63
     PTR
    -17.25
     Paige
    -17.25
    .jquery
    -17.25
    ertime
    -17.00
    Cls
    -15.44
    CLIENT
    -15.38
    ModelState
    -15.25
    PTR
    -15.19
    POSITIVE LOGITS
     depths
    24.38
    深
    24.13
    海底
    23.13
    深度
    22.13
     depth
    21.63
    Deep
    21.38
     deep
    20.63
     Deep
    20.63
    Depth
    20.38
     Depths
    20.25
    Activations Density 0.142%

    No Known Activations