© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48499
    Prev
    Next
    INDEX
    Explanations

    speciation, divergence, separation

    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
    erview
    -0.08
     Terd
    -0.07
    ernet
    -0.07
    è¿ĺåºĶ该
    -0.07
    å¾Ĺåħ¶
    -0.07
    人åıĹ伤
    -0.07
    skal
    -0.07
    PLAIN
    -0.07
    lero
    -0.07
    Ñįнд
    -0.07
    POSITIVE LOGITS
     separation
    0.10
    åĪĨ离
    0.09
     splits
    0.08
     splitting
    0.08
     separates
    0.08
    åĨįä¹Ł
    0.08
     eventual
    0.08
     eventually
    0.07
     mutual
    0.07
    æľºåĪ¶
    0.07
    Activations Density 0.002%

    No Known Activations