© 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. 42493
    Prev
    Next
    INDEX
    Explanations

    bisphosphonates and interferons

    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
    eli
    -0.08
    å°ī
    -0.07
     tentative
    -0.07
     Marshall
    -0.06
     spre
    -0.06
    çļİ
    -0.06
    å·²è¿ĩ
    -0.06
     stessa
    -0.06
    è²ī
    -0.06
    âm
    -0.06
    POSITIVE LOGITS
    åįĥç§ĭ
    0.08
    ingham
    0.08
    angk
    0.07
    erb
    0.07
    ιÏĥμοÏį
    0.07
    NCY
    0.07
    angg
    0.07
    umus
    0.07
    ]=$
    0.07
    çĤ¹å¤ļ
    0.07
    Activations Density 0.428%

    No Known Activations