© 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. 7015
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific concepts

    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
    allowed
    -0.08
    iquid
    -0.08
     allowed
    -0.07
     Allowed
    -0.07
    æĪij们ä¼ļåľ¨
    -0.07
    åĽłä¸ºåıªæľī
    -0.07
    NOP
    -0.07
    åħģ许çļĦ
    -0.07
    ãģĭãģŃ
    -0.07
    áĢģ
    -0.06
    POSITIVE LOGITS
    —even
    0.08
     iff
    0.07
     universally
    0.07
    icar
    0.07
    åĵªæĢķ
    0.07
    ÅĦczy
    0.07
    çĶļèĩ³åľ¨
    0.07
     spectacular
    0.07
     even
    0.07
     remarkably
    0.06
    Activations Density 0.045%

    No Known Activations