© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17595
    Prev
    Next
    INDEX
    Explanations

    thereafter subsequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourcem
    -0.08
    skal
    -0.08
    ãģĦãģį
    -0.07
    utow
    -0.07
    icke
    -0.07
    ä¼ł
    -0.07
    ä¸įå°±æĺ¯
    -0.07
     annunci
    -0.07
    waan
    -0.07
    ówki
    -0.07
    POSITIVE LOGITS
     thereafter
    0.16
     afterwards
    0.14
     afterward
    0.13
     subsequently
    0.12
     subsequent
    0.11
    éļıåIJİ
    0.10
     ensuite
    0.10
     anschlieÃŁend
    0.10
    çĶ±æѤ
    0.10
     further
    0.10
    Activations Density 0.349%

    No Known Activations