© 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. 33447
    Prev
    Next
    INDEX
    Explanations

    the noun that follows

    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
     اÛĮÙĨÚ©Ùĩ
    -0.09
    ä»ĸéĤ£
    -0.08
     ways
    -0.08
    她éĤ£
    -0.07
     tentu
    -0.07
    chini
    -0.07
     Ø£ÙĨÙĩÙħ
    -0.06
     often
    -0.06
     typically
    -0.06
     façon
    -0.06
    POSITIVE LOGITS
     betreff
    0.10
    ignano
    0.09
    StateChanged
    0.09
    wal
    0.08
    迪æĸ¯
    0.08
    人æľī
    0.08
    çī¹åĭĴ
    0.08
    åħ¬åı¸è§Ħ模
    0.08
    æĪijæĺ¯ä¸ª
    0.08
    äºĭæħĭ
    0.08
    Activations Density 0.187%

    No Known Activations