© 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. 20952
    Prev
    Next
    INDEX
    Explanations

    terminal fragment derivatives

    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
     нео
    -0.07
    为æıIJé«ĺ
    -0.07
    æĻĵ举
    -0.07
    redo
    -0.06
    平顺
    -0.06
    illé
    -0.06
    raid
    -0.06
    輸åħ¥
    -0.06
    å¢ŀåĩı
    -0.06
    é¢ĦéĢī
    -0.06
    POSITIVE LOGITS
    åĪĨ离
    0.13
    åĪĨéĽ¢
    0.12
    带走äºĨ
    0.10
     separation
    0.10
     fragments
    0.10
    ç¢İçīĩ
    0.09
    带走
    0.09
     separated
    0.09
     separates
    0.09
    Fragment
    0.09
    Activations Density 0.018%

    No Known Activations