© 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. 48164
    Prev
    Next
    INDEX
    Explanations

    common denominator or union

    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
    è¿ĻäºĽåĽłç´ł
    -0.08
    enho
    -0.08
    主æĮģåı¬å¼Ģ
    -0.07
    çĩ
    -0.07
    çº
    -0.07
    åIJijåīį
    -0.07
    ä»İèĢĮ使
    -0.07
    å¾Ģåīį
    -0.07
    utile
    -0.07
    _DIRECTION
    -0.07
    POSITIVE LOGITS
    åIJĪ并
    0.12
    Merge
    0.09
    缸åĬł
    0.08
    .merge
    0.08
     Merge
    0.08
    merge
    0.08
    åIJĪä½µ
    0.08
     disparate
    0.08
     merge
    0.08
     operand
    0.08
    Activations Density 0.005%

    No Known Activations