© 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. 10939
    Prev
    Next
    INDEX
    Explanations

    `.plan` followed by numbers

    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
    åĪ©çī©
    -0.07
    åĪ©äºļ
    -0.07
    çŃ
    -0.07
    ripp
    -0.07
    åīįæľŁçļĦ
    -0.06
    egah
    -0.06
    çĦ¶å¤§
    -0.06
     Aé
    -0.06
    æ½
    -0.06
    è§ij
    -0.06
    POSITIVE LOGITS
    ingle
    0.07
     Gunn
    0.07
    æĿĥåĬĽçļĦ
    0.07
    代
    0.07
     rá»iji
    0.06
    elai
    0.06
    åIJĮä¸Ĭ
    0.06
    	Dim
    0.06
    olin
    0.06
    å±ķå¼Ģåħ¨éĥ¨
    0.06
    Activations Density 0.013%

    No Known Activations