© 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. 4900
    Prev
    Next
    INDEX
    Explanations

    biodiversity and species richness

    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
     billet
    -0.08
    ansa
    -0.07
     timings
    -0.07
    adres
    -0.07
    ursa
    -0.07
    ãĤ¤ãĥ«
    -0.07
     timing
    -0.07
    idon
    -0.07
    .communication
    -0.07
    Timing
    -0.07
    POSITIVE LOGITS
     biodiversity
    0.12
     diversity
    0.12
     richness
    0.11
    çĶŁçī©å¤ļæł·æĢ§
    0.10
    å¤ļæł·æĢ§
    0.10
     Diversity
    0.09
    åIJįå½ķ
    0.09
    çī©ç§į
    0.09
    iversity
    0.09
    éŨ类
    0.09
    Activations Density 0.035%

    No Known Activations