© 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. 38218
    Prev
    Next
    INDEX
    Explanations

    whole thing

    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
     libert
    -0.07
     depart
    -0.06
    好æ±ī
    -0.06
    åĪ°æĿ¥
    -0.06
    oppel
    -0.06
    缺æįŁ
    -0.06
    ×IJ×ķת
    -0.06
    å¿ĥçľ¼
    -0.06
     dojo
    -0.06
     Gord
    -0.06
    POSITIVE LOGITS
    æķ´ä¸ªè¿ĩç¨ĭ
    0.13
    æķ´ä¸ªéĹ®é¢ĺ
    0.11
     process
    0.11
     processus
    0.10
    çļĦè¿ĩç¨ĭ
    0.10
     processo
    0.09
     folyamat
    0.09
    process
    0.09
     пÑĢоÑĨеÑģÑģа
    0.09
     entire
    0.09
    Activations Density 0.013%

    No Known Activations