© 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. 27042
    Prev
    Next
    INDEX
    Explanations

    game, events, autobiographer

    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
    azel
    -0.08
    irlo
    -0.07
    isman
    -0.06
    menta
    -0.06
    èĽ
    -0.06
    åĨį说äºĨ
    -0.06
    무
    -0.06
    åį´å¾Ī
    -0.06
    ÙĪتر
    -0.06
    ÙħØ´
    -0.06
    POSITIVE LOGITS
    geber
    0.07
    deren
    0.07
     sscanf
    0.07
    æµĻåķĨ
    0.07
    berapa
    0.07
    æľīæĪIJ
    0.07
    quia
    0.07
    à¹Īà¸Ńม
    0.06
    armo
    0.06
     rumor
    0.06
    Activations Density 0.132%

    No Known Activations