© 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. 63134
    Prev
    Next
    INDEX
    Explanations

    contrast and qualification

    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
    è¿ŀäºij
    -0.08
    åĬ¨å¼¹
    -0.08
    åį³ä½¿
    -0.07
    è´¹
    -0.07
    osen
    -0.07
     externally
    -0.07
    inger
    -0.07
    å¸ĥ
    -0.07
    à¹Īา
    -0.07
    emen
    -0.07
    POSITIVE LOGITS
    åľ¨æŁIJäºĽ
    0.11
    éĥ¨åĪĨåĨħ容
    0.10
    æľīæĿ¡ä»¶
    0.10
    åıªèĥ½è¯´
    0.09
    limited
    0.09
     Limited
    0.09
    æľīéĻIJ
    0.09
    æľīä¸Ģå®ļçļĦ
    0.08
    æľīä¸Ģå®ļ
    0.08
    主è¦ģéĽĨä¸Ńåľ¨
    0.08
    Activations Density 0.092%

    No Known Activations