© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42485
    Prev
    Next
    INDEX
    Explanations

    EXPECT 1 output table

    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
    çĴĭ
    -0.08
    å©´
    -0.08
    ozy
    -0.08
    æĺ¯å¥½
    -0.08
    OVO
    -0.08
    OVA
    -0.08
    åı¸ä»¤
    -0.07
     неме
    -0.07
    zheimer
    -0.07
    à¹Īาย
    -0.07
    POSITIVE LOGITS
    ç²¾è¯ļ
    0.07
    ete
    0.06
     Keb
    0.06
    ä¸Ģä¾ĭ
    0.06
    ä¸Ģå¹´åIJİ
    0.06
     ...
    0.06
    ê°ģ
    0.06
    etes
    0.06
    çķ¥
    0.06
     correspond
    0.05
    Activations Density 0.001%

    No Known Activations