© 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. 28035
    Prev
    Next
    INDEX
    Explanations

    proportional relationships

    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
    空空
    -0.08
    空çļĦ
    -0.08
    .Comm
    -0.08
    éĿ¢ç§¯è¾¾
    -0.07
    BOUND
    -0.07
    _unused
    -0.07
    æĸ°çĶŁ
    -0.07
    ungg
    -0.07
    ä¸įä¼ļ对
    -0.07
    apore
    -0.07
    POSITIVE LOGITS
     relationship
    0.11
     proportional
    0.10
    åħ³ç³»
    0.10
     relationships
    0.10
    åıĺéĩı
    0.10
     proportion
    0.10
    åħ³ç³»çļĦ
    0.10
     variables
    0.09
    æ¯Ķä¾ĭ
    0.09
    æĪIJæŃ£æ¯Ķ
    0.09
    Activations Density 0.002%

    No Known Activations