© 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. 51478
    Prev
    Next
    INDEX
    Explanations

    growth and multiplication

    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
    éķ¿æľŁçļĦ
    -0.09
    éķ¿æľŁä½¿çĶ¨
    -0.09
    æī£åĪĨ
    -0.08
     lowering
    -0.08
    éķ¿æľŁä»İäºĭ
    -0.08
     lowered
    -0.07
    éķ¿æľŁ
    -0.07
    磨
    -0.07
    instein
    -0.07
    éĻįä½İ
    -0.07
    POSITIVE LOGITS
    ç¿»åĢį
    0.11
     exponentially
    0.11
     exponential
    0.11
    åĢįå¢ŀ
    0.11
    çļĦå¢ŀéķ¿
    0.11
     doubling
    0.11
     grows
    0.10
     growth
    0.10
    å¢ŀéķ¿çļĦ
    0.10
    åŁºæķ°
    0.10
    Activations Density 0.010%

    No Known Activations