© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    authorship and credit

    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
     Targets
    -0.08
    λι
    -0.07
    å½±è¯Ħ
    -0.07
     targets
    -0.07
    Targets
    -0.07
    影迷
    -0.07
    Indices
    -0.07
    åľ¨å¹³æŶ
    -0.07
     Liqu
    -0.06
    æŃ£åĢ¼
    -0.06
    POSITIVE LOGITS
    ç½²åIJį
    0.12
     attribution
    0.10
     autoria
    0.10
     plagiarism
    0.09
     collaborative
    0.09
     plagiar
    0.08
     credited
    0.08
     original
    0.08
     collaborators
    0.08
    åĬŁåĬ³
    0.08
    Activations Density 0.074%

    No Known Activations