© 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. 41846
    Prev
    Next
    INDEX
    Explanations

    respectively coupled or decoupled

    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
    reed
    -0.08
    ä¸īæĿ¿
    -0.07
    eff
    -0.07
    fw
    -0.07
    è¡
    -0.07
    .names
    -0.07
    çī¹æľĹ
    -0.07
    çĶŁæķĪåIJİ
    -0.07
    ith
    -0.06
    noop
    -0.06
    POSITIVE LOGITS
     respectively
    0.08
    åĪĨåĪ«ä¸º
    0.08
    åĪĨåĪ¥æĺ¯
    0.07
    ารà¸ĸ
    0.07
    åĪĨåĪ«æĺ¯
    0.07
    enom
    0.07
    mok
    0.07
    å®Ŀå¡Ķ
    0.07
     ê°ģê°ģ
    0.07
    allon
    0.07
    Activations Density 0.114%

    No Known Activations