© 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. 30260
    Prev
    Next
    INDEX
    Explanations

    two-step process

    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
    اÙĦا
    -0.08
    äºĶç§į
    -0.08
    ä¸Ģ缮
    -0.07
    ä¸įèĢģ
    -0.07
    å¤ļç§įå¤ļæł·
    -0.07
    BOR
    -0.07
    åĩłäºº
    -0.07
    æķ´çIJĨçļĦ
    -0.07
    æķ´é½IJ
    -0.07
    åĽĽç§į
    -0.07
    POSITIVE LOGITS
     sequential
    0.18
     sequentially
    0.17
    åħĪåIJİ
    0.16
     successive
    0.15
    sequential
    0.15
    åħĪçĶ¨
    0.15
    åħĪ
    0.15
    两æŃ¥
    0.15
    åħĪå¾Ĺ
    0.14
    æĺ¯åħĪ
    0.14
    Activations Density 0.239%

    No Known Activations