© 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. 48631
    Prev
    Next
    INDEX
    Explanations

    in fact

    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
     nonetheless
    -0.08
     nevertheless
    -0.07
     natomiast
    -0.07
    ehold
    -0.07
     dagegen
    -0.07
    à¸ķรี
    -0.07
    ä½ķçŃī
    -0.07
    å¿ĥ缮ä¸ŃçļĦ
    -0.07
    меÑģÑĤи
    -0.07
    cloak
    -0.07
    POSITIVE LOGITS
     sogar
    0.09
     even
    0.09
    累累
    0.08
    erder
    0.07
     даже
    0.07
     anzi
    0.07
    ÑĬл
    0.07
     jopa
    0.07
    çĶļèĩ³åı¯ä»¥
    0.07
    并èĮĤ
    0.07
    Activations Density 0.118%

    No Known Activations