© 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. 20472
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    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
    ìĿĺ
    -0.10
    ãģ®
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    çļĦ
    -0.08
    çļĦ两
    -0.07
    ...
    -0.07
    és
    -0.07
    çļĦåħ³ç³»
    -0.07
    ذاÙĥ
    -0.07
    çļĦæłĩåĩĨ
    -0.07
    POSITIVE LOGITS
    ằn
    0.08
    åĨħ容æľī
    0.08
    nicz
    0.07
     ëĺIJíķľ
    0.07
    niec
    0.07
    auptsächlich
    0.07
    Äħtek
    0.07
    asikan
    0.07
    åĪ°çĽ®åīį
    0.07
    ikut
    0.07
    Activations Density 0.149%

    No Known Activations