© 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. 25196
    Prev
    Next
    INDEX
    Explanations

    vocational training institutions and technology programs

    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
    éĢīè°ĥçĶŁ
    -0.08
    éĻIJè´Ń
    -0.07
     Stanford
    -0.06
     Princeton
    -0.06
    åĽ´æ£ĭ
    -0.06
     lens
    -0.06
     minimalist
    -0.06
     Einstein
    -0.06
    ç¿
    -0.06
     eleg
    -0.06
    POSITIVE LOGITS
     vocational
    0.11
     Voc
    0.11
     apprentices
    0.10
    èģĮä¸ļæĬĢèĥ½
    0.10
    apprent
    0.09
    emens
    0.09
    åѦå¾Ĵ
    0.09
     Apprent
    0.09
     apprent
    0.09
    æĬĢèĥ½
    0.09
    Activations Density 0.137%

    No Known Activations