© 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. 8568
    Prev
    Next
    INDEX
    Explanations

    research and experiments

    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
    rons
    -0.07
    èµĦæºIJç½ij
    -0.07
    DOMAIN
    -0.07
    vae
    -0.07
    æıIJ
    -0.07
    åĬ¨çĿĢ
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    绿çģ¯
    -0.06
     intel
    -0.06
     geb
    -0.06
    POSITIVE LOGITS
    çłĶç©¶å·¥ä½ľ
    0.10
     experiment
    0.10
     studying
    0.10
    çłĶ究
    0.10
    çłĶ究çļĦ
    0.10
     изÑĥÑĩениÑı
    0.09
     study
    0.09
     research
    0.09
     изÑĥÑĩ
    0.09
    æĦŁåħ´è¶£çļĦ
    0.09
    Activations Density 0.483%

    No Known Activations