© 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. 58805
    Prev
    Next
    INDEX
    Explanations

    full weeks, seasons, years

    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
    çĭ¬
    -0.07
     closely
    -0.07
    leh
    -0.07
    éĩį
    -0.06
    ä»ĬçĶŁ
    -0.06
    ä¸ĢäºĮ
    -0.06
     lineage
    -0.06
    ç¼ĺ
    -0.06
     likely
    -0.06
    製
    -0.06
    POSITIVE LOGITS
    大路
    0.09
    åľ¨ä½ı
    0.08
    循çݯ
    0.08
     cycles
    0.08
    å®ļåŀĭ
    0.07
     Äijặn
    0.07
    gång
    0.07
    åĴĮéĥ¨åĪĨ
    0.07
    wald
    0.07
    yclic
    0.07
    Activations Density 0.004%

    No Known Activations