© 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. 43333
    Prev
    Next
    INDEX
    Explanations

    personal narratives and life stories

    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
     amanhã
    -0.08
    大åĬ¿
    -0.08
    ä¸ĢçĻ¾å¹´
    -0.08
    çľĭ好çļĦ
    -0.07
    æĶ»åĩ»åĬĽ
    -0.07
     proposed
    -0.07
     Casal
    -0.07
     theoretically
    -0.07
    azzi
    -0.07
    appe
    -0.07
    POSITIVE LOGITS
    çļĦç»ıåİĨ
    0.15
     experiences
    0.14
    ç»ıåİĨ
    0.13
    ç»ıåİĨçļĦ
    0.13
     experience
    0.12
    åĽŀå¿Ĩ
    0.12
    亲身ç»ıåİĨ
    0.12
     recounts
    0.11
     recount
    0.11
     memoir
    0.11
    Activations Density 0.677%

    No Known Activations