© 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. 1842
    Prev
    Next
    INDEX
    Explanations

    where variables are defined

    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
    oir
    -0.08
    åºĶåĮħæĭ¬
    -0.07
    å±ķå¼Ģåħ¨æĸĩ
    -0.07
     aka
    -0.07
    æľĢèĥ½
    -0.07
    altungen
    -0.07
    çļĦåIJĮ
    -0.07
    æĩ²
    -0.07
    åĨįæİ¥åĨį
    -0.07
    æľĢ广
    -0.07
    POSITIVE LOGITS
    osterone
    0.07
    pron
    0.07
    èĩ³ä»Ĭå·²æľī
    0.07
    igu
    0.06
    æĺ¯åħ·æľī
    0.06
    constants
    0.06
    彪
    0.06
    çªģ
    0.06
    åĽºå®ļçļĦ
    0.06
    家æĺ¯
    0.06
    Activations Density 0.054%

    No Known Activations