© 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. 65321
    Prev
    Next
    INDEX
    Explanations

    inspection, research, testing, analysis

    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
    ael
    -0.06
    alt
    -0.06
    idios
    -0.06
    è¿Ļæł·çļĦ人
    -0.06
    IER
    -0.06
    olfo
    -0.06
    ajer
    -0.06
    æľŁè´§äº¤æĺĵ
    -0.06
    å¤ĦçIJĨèĥ½åĬĽ
    -0.06
    åħ¥åĽŃ
    -0.06
    POSITIVE LOGITS
    对象
    0.14
    å°į象
    0.11
    対象
    0.10
    对象çļĦ
    0.10
     ëĮĢìĥģ
    0.10
    客ä½ĵ
    0.09
    ëĮĢìĥģ
    0.09
    Ñīаем
    0.09
     objeto
    0.09
     object
    0.08
    Activations Density 0.141%

    No Known Activations