© 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. 12809
    Prev
    Next
    INDEX
    Explanations

    creation and production

    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
    修订
    -0.08
    lott
    -0.08
    ä¸ĸçķĮ第ä¸Ģ
    -0.07
    çłĶ
    -0.07
    天ä¸ĭ第ä¸Ģ
    -0.07
    tics
    -0.07
    brook
    -0.06
     Ãļnico
    -0.06
    DATES
    -0.06
     addict
    -0.06
    POSITIVE LOGITS
     spontaneously
    0.10
     spontan
    0.10
     Creation
    0.09
     creation
    0.09
     espont
    0.08
     pairs
    0.08
     novas
    0.08
    InstantiationException
    0.08
     spontaneous
    0.08
     pair
    0.08
    Activations Density 0.008%

    No Known Activations