© 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. 7591
    Prev
    Next
    INDEX
    Explanations

    causal inference proxies

    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
    ìļ°ìĬ¤
    -0.08
    ä¿¡æģ¯ä¸¾æĬ¥
    -0.08
    lish
    -0.08
    æĪijè¦ģæĬķè¯ī
    -0.07
    æĸ°æ¦Ĥ念
    -0.07
    å¿ħåħĪ
    -0.07
    齡
    -0.07
    scenario
    -0.07
    limits
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    POSITIVE LOGITS
     proxy
    0.09
     causal
    0.08
     гоÑģ
    0.08
    æݧåĪ¶äºĨ
    0.07
    代çIJĨ
    0.07
     anonym
    0.07
     proxies
    0.07
    åįļå¼Ī
    0.07
    åľ¨åħ¨åĽ½
    0.07
    lege
    0.07
    Activations Density 0.306%

    No Known Activations