© 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. 49627
    Prev
    Next
    INDEX
    Explanations

    open loop control systems

    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
     Herm
    -0.08
    ä¸įä¹±
    -0.06
    intl
    -0.06
    åıĤçħ§
    -0.06
    -0.05
     constrain
    -0.05
    urrence
    -0.05
     Ti
    -0.05
     Obs
    -0.05
    pag
    -0.05
    POSITIVE LOGITS
    åįıåķĨä¸Ģèĩ´
    0.08
    åIJĦçݯèĬĤ
    0.08
    agai
    0.08
    avera
    0.08
    avis
    0.08
    èµĦ
    0.08
    å»ī
    0.08
    crets
    0.08
     miejs
    0.07
    åIJĦ个çݯèĬĤ
    0.07
    Activations Density 0.002%

    No Known Activations