© 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. 7114
    Prev
    Next
    INDEX
    Explanations

    digit, complexity, function, term

    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
    åħ¶ä»ĸ人
    -0.08
    åħ¶ä»ĸ人çļĦ
    -0.07
    å¸ļ
    -0.06
     Dragons
    -0.06
     latter
    -0.06
    åIJįåŃĹ
    -0.06
     LUA
    -0.06
    ä»Ģä¹Īä¸ľè¥¿
    -0.06
    aal
    -0.06
    ä»Ģä¹ĪåİŁåĽł
    -0.06
    POSITIVE LOGITS
    çĽ¡
    0.07
    丫
    0.07
    iskus
    0.07
    å°½
    0.06
     ken
    0.06
    деле
    0.06
    _mgr
    0.06
    اض
    0.06
    ÑĤва
    0.06
    交åĬŀçļĦ
    0.06
    Activations Density 0.250%

    No Known Activations