© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34807
    Prev
    Next
    INDEX
    Explanations

    entrainment, equivalence, tolerance, crystallinity

    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
    Negative Logits
    为éļ¾
    -0.08
    Fatal
    -0.08
    puter
    -0.07
     penyebab
    -0.07
     Fatal
    -0.07
    visor
    -0.07
     desid
    -0.07
    èĭ¦æīĭ
    -0.07
    åĽ°éļ¾åĴĮéĹ®é¢ĺ
    -0.07
    moz
    -0.07
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.08
    çĬ¶æĢģä¸ĭ
    0.07
    饶
    0.07
     phenomena
    0.07
    å¥ĩå¦ĻçļĦ
    0.07
    ably
    0.07
    /full
    0.06
     regime
    0.06
    æĿ¡ä»¶ä¸ĭçļĦ
    0.06
    imax
    0.06
    Activations Density 0.025%

    No Known Activations