© 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. 57142
    Prev
    Next
    INDEX
    Explanations

    difficulty or complexity

    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
     rect
    -0.09
    bauer
    -0.08
     RECT
    -0.08
    rect
    -0.08
    ä»İæľª
    -0.08
    plib
    -0.08
    кÑĥлÑĮ
    -0.07
    çĬ¹
    -0.07
    æĭŃ缮
    -0.07
    ioen
    -0.07
    POSITIVE LOGITS
    å¤įæĿĤæĢ§
    0.08
     complexities
    0.08
     complexity
    0.08
    iller
    0.08
    _COMPLEX
    0.07
    andra
    0.07
    å¤įæĿĤ度
    0.07
    è¤ĩéĽij
    0.07
     Complexity
    0.07
    å¤įæĿĤçļĦ
    0.07
    Activations Density 0.024%

    No Known Activations