© 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. 32846
    Prev
    Next
    INDEX
    Explanations

    Cushing's, hyperparathyroidism, Graves'

    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
    å©´ç«¥
    -0.09
     Nhi
    -0.08
    ikli
    -0.08
    adata
    -0.08
    ipc
    -0.07
    諦
    -0.07
    çķĻå®ĪåĦ¿ç«¥
    -0.07
     nhi
    -0.07
     Karr
    -0.07
     partida
    -0.07
    POSITIVE LOGITS
     secretion
    0.07
    æį§
    0.07
    溶
    0.07
     hyper
    0.07
    (secret
    0.07
    æĶ¶éĽĨ
    0.06
    çĦĻ
    0.06
    éĢ¢
    0.06
     aut
    0.06
    éĺ´
    0.06
    Activations Density 0.071%

    No Known Activations