© 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. 55130
    Prev
    Next
    INDEX
    Explanations

    code structure closing tags

    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
    aal
    -0.07
    orig
    -0.07
    æĹłå½±
    -0.07
    为ä¸Ģä½ĵçļĦ
    -0.07
    alias
    -0.07
    _SEPARATOR
    -0.06
    ointment
    -0.06
    壽
    -0.06
    alloc
    -0.06
     Afin
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀľæĺ¯
    0.08
    æľĢç»Ī
    0.07
    CACHE
    0.07
     tats
    0.07
    assen
    0.07
     final
    0.07
    æķ´ä½ĵ
    0.07
    ivated
    0.07
    ç»ĵæŀľä¸º
    0.07
    velle
    0.07
    Activations Density 0.004%

    No Known Activations