© 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. 23145
    Prev
    Next
    INDEX
    Explanations

    counting or sequences

    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
     Baby
    -0.06
    Ľ
    -0.06
    igh
    -0.06
     rel
    -0.06
    ighet
    -0.06
    Baby
    -0.06
    fish
    -0.06
    fertig
    -0.06
    виÑħ
    -0.06
    oli
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.07
    _IW
    0.07
    azan
    0.06
    æĥij
    0.06
    eler
    0.06
    ISCO
    0.06
    ablo
    0.06
    alian
    0.06
    åįıä¼ļä¼ļåijĺ
    0.06
    ÙĪÛķ
    0.06
    Activations Density 0.057%

    No Known Activations