© 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. 32370
    Prev
    Next
    INDEX
    Explanations

    fatty liver disease, metabolic syndrome, obesity

    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
    çŁ
    -0.08
    ifr
    -0.08
    åħ¶æīĢ
    -0.07
     themselves
    -0.07
    ä¸ĩéĩĮ
    -0.07
     signin
    -0.07
    angeb
    -0.07
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.07
    opr
    -0.07
     revan
    -0.07
    POSITIVE LOGITS
    urb
    0.06
    efeld
    0.06
    ngle
    0.06
    å°ıäºĭ
    0.06
     Slater
    0.06
    æĢ»ä¹ĭ
    0.06
    aked
    0.06
    uhe
    0.05
    ä¸ĵä¸ļçļĦ
    0.05
    åĬŁèĥ½æĺ¯
    0.05
    Activations Density 0.001%

    No Known Activations