© 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. 21354
    Prev
    Next
    INDEX
    Explanations

    comparisons of degree

    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
    æ¯Ķ以å¾Ģ
    -0.08
    estal
    -0.08
    Ïĥκ
    -0.08
    least
    -0.08
    ä»ĬæľĿ
    -0.08
    окÑģи
    -0.08
    agraph
    -0.08
    inste
    -0.07
    æ¯Ķ以åīį
    -0.07
    agement
    -0.07
    POSITIVE LOGITS
     بÙĥØ«ÙĬر
    0.10
    没éĤ£ä¹Ī
    0.09
    没æľīéĤ£ä¹Ī
    0.08
     than
    0.08
    ä¸İæѤ
    0.08
    å¾Ĺå¤ļ
    0.07
    ãģ¾ãģĹãģ¦
    0.07
    -than
    0.07
    äºİæѤ
    0.07
    ä¸įçĦ¶
    0.07
    Activations Density 0.118%

    No Known Activations