© 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. 4823
    Prev
    Next
    INDEX
    Explanations

    causes and complications

    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
    çĤľ
    -0.08
    çĨĻ
    -0.07
    omor
    -0.07
    Ïģκ
    -0.07
     endowed
    -0.07
    åı¸å¾Ĵ
    -0.06
    ascal
    -0.06
     implicitly
    -0.06
    omics
    -0.06
    å¤ŁçĶ¨
    -0.06
    POSITIVE LOGITS
     caused
    0.12
    åı¯èĥ½å¯¼èĩ´
    0.12
     improperly
    0.11
     improper
    0.11
    导èĩ´
    0.11
    导èĩ´çļĦ
    0.11
    ä¹Łä¼ļ导èĩ´
    0.11
    ä¼ļ导èĩ´
    0.11
     causes
    0.10
    è¿ĻäºĽéĹ®é¢ĺ
    0.10
    Activations Density 0.039%

    No Known Activations