© 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. 38857
    Prev
    Next
    INDEX
    Explanations

    note:

    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
    auses
    -0.07
    IVEN
    -0.07
    ä»ĸ便
    -0.07
    iven
    -0.07
    ĥĿ
    -0.07
     addirittura
    -0.07
     إذÙĨ
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
     بدÙĪرÙĩ
    -0.07
    çľĭçľĭåIJ§
    -0.07
    POSITIVE LOGITS
    ä¸įæĺ¯ä»Ģä¹Ī
    0.10
    ä¸įæĺ¯è¯´
    0.09
    æѤ
    0.09
    決ãģĹãģ¦
    0.09
    éĩıåĬĽ
    0.08
    ãģĤãģı
    0.08
     not
    0.08
    并éĿŀ
    0.08
    並ä¸įæĺ¯
    0.08
    æŃ¤é¡¹
    0.07
    Activations Density 0.084%

    No Known Activations