© 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. 10381
    Prev
    Next
    INDEX
    Explanations

    external fields, forces, or stimuli

    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
    åħ¶äºº
    -0.07
    elai
    -0.07
    太åĴĮ
    -0.07
    åĴĮç»´çĶŁç´ł
    -0.07
    æŃ£å¸¸ä½¿çĶ¨
    -0.07
    omini
    -0.07
    常åĬ¡çIJĨäºĭ
    -0.07
    ODO
    -0.07
    åĿĬ
    -0.07
    è·Łåįķ
    -0.07
    POSITIVE LOGITS
    å¤ĸåĬĽ
    0.10
    å¤ĸéĥ¨
    0.09
     externos
    0.09
    /internal
    0.08
     external
    0.08
     externally
    0.08
    çļĦå¤ĸéĥ¨
    0.08
     خارجÙĬØ©
    0.08
    å¤ĸçķĮ
    0.08
     externas
    0.08
    Activations Density 0.023%

    No Known Activations