© 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. 9848
    Prev
    Next
    INDEX
    Explanations

    hollow structures

    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
    ulp
    -0.07
    åijĬ
    -0.07
    å°º
    -0.07
    æĹłæĿ¡ä»¶
    -0.07
    æ±ĩ
    -0.07
    çĥĤ
    -0.07
    ç´§
    -0.06
    æķ´ä¸ªéĹ®é¢ĺ
    -0.06
    caler
    -0.06
    桥头
    -0.06
    POSITIVE LOGITS
     hollow
    0.13
     Hollow
    0.12
    ä¸Ń空
    0.12
    空å¿ĥ
    0.11
    空çļĦ
    0.10
    空èĻļ
    0.10
    空æ´ŀ
    0.09
    壳
    0.09
    ollow
    0.09
     emptied
    0.09
    Activations Density 0.081%

    No Known Activations