© 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. 55452
    Prev
    Next
    INDEX
    Explanations

    appreciation and thoughtful actions

    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
    éªĭ
    -0.08
    åħ·å¤ĩä¸Ģå®ļçļĦ
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    åĭī强
    -0.07
    å±ĬæŶ
    -0.07
     hopefully
    -0.07
    çIJĨ论ä¸Ĭ
    -0.07
    egos
    -0.07
    _Module
    -0.07
    侥幸
    -0.07
    POSITIVE LOGITS
    æĹłç§ģçļĦ
    0.12
     tirelessly
    0.10
    没æľīä¸Ŀ毫
    0.09
    åį³ä½¿åľ¨
    0.09
     patiently
    0.09
    çĻ¾å¿Ļ
    0.08
    ä¸į顾
    0.08
    ä¸įæĥľ
    0.08
    çļĦ身影
    0.08
    æĹłç§ģ
    0.08
    Activations Density 0.230%

    No Known Activations