© 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. 39640
    Prev
    Next
    INDEX
    Explanations

    written as

    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
    lify
    -0.08
    ç¼®
    -0.07
    ä¸įä½Ĩ
    -0.07
    æ¯Ķèµ·æĿ¥
    -0.07
     ensuing
    -0.07
    åĨįæ·»
    -0.07
    ä¸į管æĺ¯
    -0.07
    éľ
    -0.07
    mium
    -0.07
    anity
    -0.07
    POSITIVE LOGITS
    å½¢å¼ı
    0.08
    opa
    0.07
    ëĮĢë¡ľ
    0.07
     sebagai
    0.07
    æĪIJè¿Ļæł·
    0.07
    èĮĥåĦ¿
    0.06
    affer
    0.06
    epen
    0.06
    ored
    0.06
     form
    0.06
    Activations Density 0.051%

    No Known Activations