© 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. 14511
    Prev
    Next
    INDEX
    Explanations

    composers or clothing designers

    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
    èı
    -0.08
    åħĪçĶŁ
    -0.07
    rim
    -0.07
    edt
    -0.07
    éĴµ
    -0.06
    åħĪçĶŁçļĦ
    -0.06
    bras
    -0.06
    ges
    -0.06
    æŃ¤æ¥¼
    -0.06
    æĪijè¿ĺè¦ģ
    -0.06
    POSITIVE LOGITS
    ï¼ĮãĢĬ
    0.09
     documented
    0.08
    åıĤè§ģ
    0.08
    æį®
    0.08
    åıĤèĢĥèµĦæĸĻ
    0.08
    è§ģäºİ
    0.08
     à¸Ķัà¸ĩ
    0.08
    :http
    0.07
     })(
    0.07
    åı¯ä»¥åıĤèĢĥ
    0.07
    Activations Density 0.143%

    No Known Activations