© 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. 58744
    Prev
    Next
    INDEX
    Explanations

    child and bone growth

    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
     hashed
    -0.08
    éħĿ
    -0.08
    emade
    -0.08
    è¯ĹéĽĨ
    -0.07
    _DEPTH
    -0.07
    bile
    -0.07
     vegas
    -0.07
    athi
    -0.07
    éľ¾
    -0.07
    dispatch
    -0.07
    POSITIVE LOGITS
     growth
    0.13
     Growth
    0.11
    growth
    0.11
    çĶŁéķ¿
    0.11
    追赶
    0.10
     ìĦ±ìŀ¥
    0.10
     Wachstum
    0.09
    éķ¿å¤§
    0.09
    çļĦçĶŁéķ¿
    0.09
     ìĦ±ìŀ¥ìĿĦ
    0.09
    Activations Density 0.072%

    No Known Activations