© 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. 39742
    Prev
    Next
    INDEX
    Explanations

    DNA replication origins and stress

    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
    æĮ¯åįİ
    -0.08
    京
    -0.07
    VS
    -0.07
    duino
    -0.07
    Lean
    -0.07
    ikka
    -0.07
    积
    -0.07
    ç»´
    -0.06
    æĮĤçīĮ
    -0.06
     Gym
    -0.06
    POSITIVE LOGITS
    å¿ħé¡»çĶ±
    0.08
    ợ
    0.08
    ÏĢη
    0.08
     Soares
    0.08
    à°¤à±į
    0.08
    BuilderFactory
    0.07
    åĽ¾ç½ij
    0.07
    活水
    0.07
    kker
    0.07
    éĥ½åģļ
    0.07
    Activations Density 0.006%

    No Known Activations