© 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. 29558
    Prev
    Next
    INDEX
    Explanations

    semiconductor mobility degradation

    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
    æ´»åĬ¨åĨħ容
    -0.07
    ocol
    -0.07
    ç½IJ
    -0.06
    rée
    -0.06
    äºĭçļĦ
    -0.06
    XML
    -0.06
    è¡įçĶŁåĵģ
    -0.06
     ìĭłíķľ
    -0.06
    èv
    -0.06
    éĢļåĪĻ
    -0.06
    POSITIVE LOGITS
     silicon
    0.09
     rasse
    0.08
    æĻ¶
    0.08
    éĽĨæĪIJçĶµè·¯
    0.08
     crystal
    0.08
    æĻ¶ä½ĵ管
    0.08
    åĻ¨ä»¶
    0.08
    å¾®çĶµåŃIJ
    0.08
    åįĬ导ä½ĵ
    0.08
    æĻ¶ä½ĵ
    0.08
    Activations Density 0.009%

    No Known Activations