© 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. 4545
    Prev
    Next
    INDEX
    Explanations

    teacher learning alignment

    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
    iros
    -0.08
    relude
    -0.07
    大åѦæ¯ķä¸ļ
    -0.07
    éĺ²èĮĥæĦıè¯Ĩ
    -0.07
    ä¿ĿæĬ¤èĩªå·±
    -0.07
    åѦåĪ°äºĨå¾Īå¤ļ
    -0.07
    ifestyles
    -0.07
    åĽ¢ç»ĵä¸Ģèĩ´
    -0.07
    çĶŁæ´»æĸ¹å¼ı
    -0.07
    æıIJé«ĺèѦæĥķ
    -0.07
    POSITIVE LOGITS
    åĽłæĿIJæĸ½æķĻ
    0.11
    è¢«ä¾ĽåºĶåķĨ
    0.10
    ä¿ĥè¿ĽåѦçĶŁ
    0.09
    æķĻå¸Ī
    0.09
    å®ŀæĸ½çļĦ
    0.09
    å¸ĥç½®
    0.09
    å®ŀæĸ½
    0.09
    åĽłæĿIJ
    0.08
     teacher
    0.08
     scaffold
    0.08
    Activations Density 0.523%

    No Known Activations