© 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. 24174
    Prev
    Next
    INDEX
    Explanations

    conditions and medical terms

    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
    ستا
    -0.08
    Feels
    -0.08
    æīĢ欲
    -0.08
    ELO
    -0.07
    isso
    -0.07
    ovina
    -0.07
    åħ«å¤§
    -0.07
    omics
    -0.07
    urning
    -0.07
    FieldValue
    -0.07
    POSITIVE LOGITS
     respectively
    0.08
    åīįèĢħ
    0.07
    éĢļè¿ĩè¿ĻäºĽ
    0.07
    åĪĨåĪ«æĺ¯
    0.07
    ãģĿãĤĮãģŀãĤĮ
    0.07
    åĪĨåĪ«ä»İ
    0.07
     respectiv
    0.06
    åĪĨåĪ«ä¸İ
    0.06
     (&
    0.06
     tons
    0.06
    Activations Density 0.285%

    No Known Activations