© 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. 52223
    Prev
    Next
    INDEX
    Explanations

    re-evaluation or testing

    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
    aget
    -0.07
    纵åIJij
    -0.07
     Macro
    -0.07
    mic
    -0.07
    Macro
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.06
    离åĪ«
    -0.06
     macro
    -0.06
    kil
    -0.06
    keh
    -0.06
    POSITIVE LOGITS
     recal
    0.09
    çħ§æł·
    0.09
    still
    0.09
     still
    0.09
    ä»įçĦ¶
    0.09
    è¿Ļæł·ä¸ĢæĿ¥
    0.08
     Still
    0.08
    ä»į以
    0.08
    åıįèĢĮä¼ļ
    0.08
    æľ±åħĥ
    0.08
    Activations Density 0.171%

    No Known Activations