© 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. 8553
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and structures

    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
    ëĤĺë§Ī
    -0.08
    æĨ¬
    -0.08
    ÙĨÙĬÙģ
    -0.08
    aderos
    -0.07
    æł©æł©
    -0.07
     Trou
    -0.07
    oldown
    -0.07
    usan
    -0.07
    使çĶ¨è¯¥
    -0.07
    égard
    -0.07
    POSITIVE LOGITS
    èĢĮæĪIJçļĦ
    0.11
    èĢĮæĪIJ
    0.10
    ç»ĦæĪIJçļĦ
    0.10
    å½¢æĪIJä¸Ģ个
    0.09
    æŀĦæĪIJçļĦ
    0.09
    å½¢æĪIJçļĦ
    0.08
     подÑĢÑıд
    0.08
    å½¢æĪIJ
    0.08
    ç»ĦæĪIJ
    0.08
    åıł
    0.08
    Activations Density 0.082%

    No Known Activations