© 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. 662
    Prev
    Next
    INDEX
    Explanations

    electrophilic intermediates, redness, temporary states

    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
    NSObject
    -0.08
    è¾ĵ
    -0.08
     libertin
    -0.08
    ousand
    -0.08
    bu
    -0.07
    润èĤº
    -0.07
    urz
    -0.07
    濯
    -0.07
    å¿ĥå¦Ĥ
    -0.07
    ovah
    -0.07
    POSITIVE LOGITS
     temporary
    0.10
    temporary
    0.09
     temporarily
    0.08
     momentarily
    0.08
    æļĤæŶçļĦ
    0.07
     temporaire
    0.07
     ÙħؤÙĤت
    0.07
     Temporary
    0.07
    tmp
    0.07
    Temporary
    0.07
    Activations Density 0.001%

    No Known Activations