© 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. 10531
    Prev
    Next
    INDEX
    Explanations

    medical conditions and USA

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    éder
    -0.07
    -0.07
    _validator
    -0.07
    çļĦåij¢
    -0.07
    corre
    -0.07
    tagon
    -0.07
    neur
    -0.06
     Lors
    -0.06
    .eps
    -0.06
    POSITIVE LOGITS
    zim
    0.08
    ãĥĬãĥ³
    0.07
    jim
    0.07
    ertas
    0.07
    ×ķ×ĸ
    0.07
    ulu
    0.07
     Mum
    0.06
    gara
    0.06
    第ä¸Ģåľº
    0.06
    ÙĪاÙĨ
    0.06
    Activations Density 0.571%

    No Known Activations