© 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. 32887
    Prev
    Next
    INDEX
    Explanations

    scattering, interaction, lasers, mirror

    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
    ä¸ĢæŦåĩºçİ°
    -0.08
    æĹ
    -0.07
    ä¸įå¹²
    -0.07
     homos
    -0.07
    ä¸įå¾Ĺä»İäºĭ
    -0.07
    rawer
    -0.07
    .house
    -0.07
    utang
    -0.07
    issen
    -0.07
    äºĭæĪIJ
    -0.07
    POSITIVE LOGITS
    çļ®çIJĥ
    0.08
     scattering
    0.07
    inos
    0.07
     interaction
    0.07
    çIJĥèĽĭçĻ½
    0.07
     recoil
    0.07
     interactions
    0.07
    interaction
    0.07
    ä½Ľ
    0.06
     ngh
    0.06
    Activations Density 0.001%

    No Known Activations