© 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. 47436
    Prev
    Next
    INDEX
    Explanations

    ML

    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
    ลà¹Į
    -0.07
    ĤŃ
    -0.07
    atron
    -0.06
    æľīçĸijéĹ®
    -0.06
    ä¸į解
    -0.06
    æľ¬èº«çļĦ
    -0.06
    æĪijåıĪ
    -0.06
    _heap
    -0.06
    ī´
    -0.06
    ãģħ
    -0.06
    POSITIVE LOGITS
    داÙĨ
    0.08
    å¼¹
    0.08
    à¤ľà¤¾
    0.08
    ULO
    0.08
    еÑĢи
    0.07
    ulo
    0.07
    uelas
    0.07
    ç«ĭ足
    0.07
     Cin
    0.07
    cin
    0.07
    Activations Density 0.031%

    No Known Activations