© 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. 60068
    Prev
    Next
    INDEX
    Explanations

    mold, bacteria, multiply, dry

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èĮ¶æĿ¯
    -0.08
     indiv
    -0.07
    opf
    -0.07
    æ¿ĢåĬ¨
    -0.07
    使å¾Ĺ
    -0.07
     Magnum
    -0.06
    æĿŁ
    -0.06
    æĬĽ
    -0.06
    icycle
    -0.06
    çıĤ
    -0.06
    POSITIVE LOGITS
    æ»ĭçĶŁ
    0.16
    éľīèıĮ
    0.10
    æ»ĭ
    0.10
     unchecked
    0.10
    湿æ°Ķ
    0.10
     stagn
    0.10
    ç»ĨèıĮ
    0.09
     stagnant
    0.09
    çĹħèıĮ
    0.09
     bacteria
    0.09
    Activations Density 0.066%

    No Known Activations