© 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. 55050
    Prev
    Next
    INDEX
    Explanations

    by variable or lambda

    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
    ç¶ļãģįãĤĴèªŃãĤĢ
    -0.07
    à¥Ĥ
    -0.06
    aker
    -0.06
     somehow
    -0.06
    å¾Īå¤ļæŶåĢĻ
    -0.06
     GetLastError
    -0.06
    缴æİ¥å°Ĩ
    -0.06
     com
    -0.06
    æij©æ´Ľ
    -0.06
    .removeListener
    -0.06
    POSITIVE LOGITS
    zem
    0.08
    ://%
    0.08
    amaz
    0.07
    asen
    0.07
    ":[{"
    0.07
     Kred
    0.07
    ENN
    0.07
    asuk
    0.06
    æ´¾
    0.06
    etter
    0.06
    Activations Density 0.004%

    No Known Activations