© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7521
    Prev
    Next
    INDEX
    Explanations

    memories and nostalgia

    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
    æĦıæĢĿ
    -0.07
    -headed
    -0.07
    çľĭ好çļĦ
    -0.06
    à¹ģร
    -0.06
    áp
    -0.06
    cors
    -0.06
    oley
    -0.06
     вÑĭÑħоде
    -0.06
    ozilla
    -0.06
    缮çŀªåı£åijĨ
    -0.06
    POSITIVE LOGITS
     memories
    0.19
     Memories
    0.16
    åĽŀå¿Ĩ
    0.16
     memory
    0.16
    è®°å¿Ĩ
    0.15
    å¾Ģäºĭ
    0.15
    è®°å¿ĨçļĦ
    0.14
    memory
    0.14
    Memory
    0.14
    追å¿Ĩ
    0.14
    Activations Density 0.137%

    No Known Activations