© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    genetic and medical conditions

    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
    uru
    -0.08
     Scot
    -0.06
    çĸĹ
    -0.06
    é¦ĭ
    -0.06
    styl
    -0.06
    ä¸Ģ个女人
    -0.06
    ãĤ¦ãĤ©
    -0.06
    è¿Ļç§įè¡Į为
    -0.06
    çĪĨäºĨ
    -0.06
    édé
    -0.06
    POSITIVE LOGITS
     combinations
    0.10
    åIJĪ
    0.08
     combina
    0.08
     Combination
    0.08
     combos
    0.08
    ç»ĦåIJĪ
    0.08
    ValuePair
    0.08
    lai
    0.08
     inherit
    0.08
    omo
    0.08
    Activations Density 0.001%

    No Known Activations