© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    matrix notation and arrays

    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
    å¨ħ
    -0.06
    ụt
    -0.06
    ¢
    -0.06
    åŀ«
    -0.06
    zano
    -0.06
    /cs
    -0.06
     transit
    -0.06
     bocca
    -0.06
    æŁIJä¸Ģ个
    -0.06
    两边çļĦ
    -0.06
    POSITIVE LOGITS
    ieste
    0.09
    ?,?,
    0.08
     herr
    0.07
    orex
    0.07
    uds
    0.07
    ikan
    0.07
    çĪ¶
    0.07
    åij¢
    0.07
    isi
    0.07
    éĩįéĩį
    0.07
    Activations Density 0.009%

    No Known Activations