© 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. 54957
    Prev
    Next
    INDEX
    Explanations

    code separators

    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
    atine
    -0.07
    inach
    -0.07
    stens
    -0.07
    atin
    -0.06
     بخ
    -0.06
    åħĦ妹
    -0.06
    并积æŀģ
    -0.06
    akon
    -0.06
    .tell
    -0.06
    Hi
    -0.06
    POSITIVE LOGITS
    try
    0.08
    ammers
    0.07
     sosten
    0.07
    encent
    0.07
    对
    0.07
     for
    0.07
    çĽ²
    0.07
    æĿ¡æĿ¡
    0.06
    urut
    0.06
    ABC
    0.06
    Activations Density 0.058%

    No Known Activations