© 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. 58932
    Prev
    Next
    INDEX
    Explanations

    product-form solutions

    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
    åı¯ä½ľä¸º
    -0.07
    rans
    -0.07
    ciano
    -0.07
    ostro
    -0.07
    mium
    -0.07
    mok
    -0.07
    +xml
    -0.07
    rides
    -0.07
    éĺ»
    -0.06
    äºĶæĺŁçº§
    -0.06
    POSITIVE LOGITS
     iterator
    0.09
    جÙħع
    0.09
     indexing
    0.08
     iterators
    0.08
     counting
    0.08
    rag
    0.08
    Iterator
    0.08
     summ
    0.08
     shifted
    0.07
    è¿Ń代
    0.07
    Activations Density 0.007%

    No Known Activations