© 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. 1127
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs and constants

    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
    åĽŀçŃĶéĩı
    -0.08
    ehan
    -0.08
    ++++++++++++++++++++++++++++++++
    -0.08
    VISIBLE
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
     coragem
    -0.08
    è¸Ĭ
    -0.08
    DataContext
    -0.08
    ЧÐĺ
    -0.08
    udiante
    -0.08
    POSITIVE LOGITS
     min
    0.08
    min
    0.07
     K
    0.07
    ç´§
    0.07
    .min
    0.06
     max
    0.06
    æľĢä¼ĺ
    0.06
    éĩijèĬ±
    0.06
    K
    0.06
     Del
    0.06
    Activations Density 0.004%

    No Known Activations