© 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. 49407
    Prev
    Next
    INDEX
    Explanations

    age group

    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
    æľĢä½İåѦåİĨ
    -0.09
    ahal
    -0.07
    alak
    -0.07
    awang
    -0.07
    æ¯ıå¹³æĸ¹ç±³
    -0.07
    大è¯Ŀ
    -0.07
    ijnen
    -0.07
    å¾ĹåĬĽ
    -0.07
    yim
    -0.07
     Vaticano
    -0.07
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.17
     age
    0.17
    é¾Ħ
    0.15
     ages
    0.14
    _age
    0.14
    -age
    0.13
    -aged
    0.13
     Age
    0.13
    年纪
    0.13
    å¹´é¾Ħ段
    0.13
    Activations Density 0.413%

    No Known Activations