© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48320
    Prev
    Next
    INDEX
    Explanations

    disease, disorder, virus

    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
    ospace
    -0.07
    nof
    -0.07
    ãģĨãģ¡ãģ«
    -0.07
    bland
    -0.07
    鼨ä¸Ń
    -0.07
    _ITER
    -0.07
    èļ¤
    -0.07
    agus
    -0.06
    æµģåħī
    -0.06
    hints
    -0.06
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.08
    åıªè¦ģåľ¨
    0.08
     affecting
    0.07
     widespread
    0.07
    ÑĢеÑĨ
    0.07
     recess
    0.07
    ç½ķè§ģ
    0.07
    åħĪåľ¨
    0.07
    onia
    0.07
    åľ¨æŁIJ
    0.07
    Activations Density 0.034%

    No Known Activations