© 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. 48691
    Prev
    Next
    INDEX
    Explanations

    numerical phase, kinetic, familiar landmarks

    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
    æķħä½ľ
    -0.07
    URAL
    -0.07
    ÏĦÏģÏĮ
    -0.07
    èī¯ä¹ħ
    -0.07
    idden
    -0.07
    åĽ¢èģļ
    -0.07
    istributed
    -0.06
    å±±åŁİ
    -0.06
    Ģ
    -0.06
    çµ®
    -0.06
    POSITIVE LOGITS
    æ··æIJŃ
    0.08
    åı¦ä¸Ģæĸ¹
    0.08
    ä¸Ģæĸ¹
    0.08
    åı¦ä¸Ģè¾¹
    0.08
    éĶ¢
    0.07
    while
    0.07
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    0.07
    åħ¶ä»ĸæĸ¹å¼ı
    0.07
    :]
    0.07
    æ··åIJĪ
    0.07
    Activations Density 0.075%

    No Known Activations