© 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. 10517
    Prev
    Next
    INDEX
    Explanations

    age-related descriptions

    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
     девÑĥÑĪка
    -0.09
    å®ŀä¹łæľŁéĹ´
    -0.09
    å¯ĮäºĮ代
    -0.08
    -girl
    -0.08
     tyttö
    -0.08
     createElement
    -0.08
    ãĥIJãĤ¤ãĥĪ
    -0.08
    girl
    -0.08
     девÑĥ
    -0.08
    å§ijå¨ĺ
    -0.08
    POSITIVE LOGITS
    èĢģå¹´
    0.22
    éĢĢä¼ij
    0.21
    æĻļå¹´
    0.20
    éĢĢä¼ijåIJİ
    0.19
     aging
    0.19
    èĢģ年人
    0.18
    èĢģäºĨ
    0.18
    èĢģ年人çļĦ
    0.18
     retirement
    0.18
     retired
    0.18
    Activations Density 1.021%

    No Known Activations