© 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. 18609
    Prev
    Next
    INDEX
    Explanations

    system/program names

    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
    _ISO
    -0.08
    éric
    -0.08
    人äºĭèĢĥè¯ķ
    -0.07
    ås
    -0.07
    ä¸ĢåIJij
    -0.07
     recus
    -0.07
    ozen
    -0.07
    èĮĥåĦ¿
    -0.07
     competency
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    POSITIVE LOGITS
    çĭ¬å®¶
    0.08
    ç§ĺ
    0.08
     genuine
    0.07
    è½°åĬ¨
    0.07
    å½»åºķ
    0.07
    æĹłä»»ä½ķ
    0.07
    åĤ³å¥ĩ
    0.07
    åħ¨åĽ½ç»Łä¸Ģ
    0.07
     consortium
    0.07
    饮
    0.07
    Activations Density 0.190%

    No Known Activations