© 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. 26499
    Prev
    Next
    INDEX
    Explanations

    full or complete cycle

    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
    кина
    -0.08
    çĶ¨ä¹¦
    -0.08
    opedia
    -0.08
    ä¸īå°º
    -0.08
    inom
    -0.08
    çģ«äºĨ
    -0.07
    æĺŁäºº
    -0.07
    apore
    -0.07
    jab
    -0.07
    ä¸ĢæĻĤ
    -0.07
    POSITIVE LOGITS
     cycle
    0.17
    循çݯ
    0.14
     Cycle
    0.14
    åij¨æľŁ
    0.14
    å®Įæķ´
    0.14
    å®Įæķ´çļĦ
    0.14
     cycles
    0.14
    _cycle
    0.14
    cycle
    0.13
    åij¨æľŁçļĦ
    0.13
    Activations Density 0.026%

    No Known Activations