© 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. 25970
    Prev
    Next
    INDEX
    Explanations

    version and quality settings

    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
    ulf
    -0.08
    uÄĩ
    -0.07
    æ¯Ķä¾ĭçļĦ
    -0.07
    æ¨ĭ
    -0.07
    etch
    -0.07
    åįĬè¾¹
    -0.07
    ÙĩÙĨ
    -0.07
    å°±åĪ°
    -0.07
    à¸łà¸²à¸£
    -0.07
    æ¯ĽåŃĶ
    -0.07
    POSITIVE LOGITS
    kunft
    0.07
    orien
    0.07
    MenuBar
    0.07
    æŁ³
    0.07
    ienz
    0.07
    让åĪ«äºº
    0.07
    irurg
    0.07
    让è§Ĥä¼Ĺ
    0.06
     Rosen
    0.06
    âĸĪâĸĪ
    0.06
    Activations Density 0.001%

    No Known Activations