© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57656
    Prev
    Next
    INDEX
    Explanations

    species dominance

    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
    缸åħ³äººåijĺ
    -0.07
    æĥij
    -0.07
     обла
    -0.06
    åıijç»Ļ
    -0.06
    çī
    -0.06
     Org
    -0.06
    å¸ĪèµĦ
    -0.06
    kets
    -0.06
    uvat
    -0.06
    æľŁéĻIJ
    -0.06
    POSITIVE LOGITS
    -dominated
    0.11
    æĢ»æķ°çļĦ
    0.09
     dominance
    0.09
     species
    0.09
    species
    0.09
     Æ°a
    0.09
    èĥĨåŃIJ
    0.08
     newcomers
    0.08
    адÑĮ
    0.08
    ç§įç±»
    0.08
    Activations Density 0.128%

    No Known Activations