© 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. 44373
    Prev
    Next
    INDEX
    Explanations

    -centric, -ical, -level, quality, practice

    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
    licherweise
    -0.09
     Mots
    -0.08
    ablemente
    -0.08
    ạm
    -0.07
    olla
    -0.07
    ivamente
    -0.07
    ligen
    -0.07
    大èĩ´
    -0.07
     Mehrheit
    -0.07
     غاÙĦ
    -0.07
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.08
    izable
    0.08
    å¾Ĺèµ·
    0.08
    istic
    0.08
    ذج
    0.08
    以èĩ³äºİ
    0.07
    å¾Ĺä½ı
    0.07
    å®ŀåĪĻ
    0.07
    ocratic
    0.07
    istical
    0.07
    Activations Density 0.262%

    No Known Activations