© 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. 37829
    Prev
    Next
    INDEX
    Explanations

    Cuban, Zika, Rey, omon, erm, les

    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
    Å©a
    -0.08
    êµī
    -0.07
    å¸ħæ°ĶçļĦ
    -0.07
    ãĪľ
    -0.07
    亿人æ°ijå¸ģ
    -0.07
     álla
    -0.07
    íĺ
    -0.06
     bedan
    -0.06
    åĽ½è¶³
    -0.06
    ä¸ĩ人æ°ijå¸ģ
    -0.06
    POSITIVE LOGITS
    æ¯į女
    0.06
    é©»åįİ
    0.06
     yOffset
    0.05
     mouseY
    0.05
    èļĮ
    0.05
     اÙĦÙĨصر
    0.05
     nhan
    0.05
    ãģ«è¡Įãģ£ãģ¦ãģįãģ¾ãģĹãģŁ
    0.05
    çŃīåĽ½éĻħ
    0.05
    å¨ĺ家
    0.05
    Activations Density 12.402%

    No Known Activations