© 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. 23395
    Prev
    Next
    INDEX
    Explanations

    T1 relaxation time / half-life

    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
    IMIZE
    -0.08
    åIJµ
    -0.07
    举éĺ³
    -0.07
     충
    -0.07
    声ä¸Ń
    -0.07
    teil
    -0.07
    å°ıå¹ħ
    -0.07
    ecke
    -0.07
    åįłäºĨ
    -0.07
    robat
    -0.07
    POSITIVE LOGITS
    зеÑĢ
    0.08
    ä»ĭ
    0.08
    éķ¿çŁŃ
    0.07
     Tavern
    0.07
     invers
    0.07
    inverse
    0.07
     inverse
    0.07
    ulette
    0.07
    ä¸įè¿ľ
    0.07
    اء
    0.07
    Activations Density 0.023%

    No Known Activations