© 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. 7366
    Prev
    Next
    INDEX
    Explanations

    creation and beginning of the world

    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
    urop
    -0.08
    éĺµåľ°
    -0.08
    _beam
    -0.08
    untr
    -0.07
    udies
    -0.07
    æķĻåŃ¦æ°´å¹³
    -0.07
    è¿Ĥ
    -0.07
    æ²½
    -0.07
     perso
    -0.07
    丢äºĨ
    -0.07
    POSITIVE LOGITS
     creation
    0.11
     Creation
    0.11
    éĢłçī©
    0.10
    ä¸ĩçī©
    0.10
    creation
    0.10
    åĪĽéĢł
    0.10
    éĢł
    0.09
    Creation
    0.09
     창조
    0.09
     creator
    0.09
    Activations Density 0.014%

    No Known Activations