© 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. 46567
    Prev
    Next
    INDEX
    Explanations

    word endings and forms

    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
    örg
    -0.07
    auss
    -0.06
    লা
    -0.06
    auer
    -0.06
    çŃīçī¹çĤ¹
    -0.06
    orge
    -0.06
    ä½Ĩä¸įæĺ¯
    -0.06
    HP
    -0.06
    au
    -0.06
    ynch
    -0.06
    POSITIVE LOGITS
     Sond
    0.07
    ÛĮدÙĨ
    0.07
    æĹłäºĭ
    0.07
    äºĭ
    0.07
     Huckabee
    0.07
    .jquery
    0.07
     kats
    0.07
    onii
    0.07
     Dau
    0.07
    ÌĢ
    0.07
    Activations Density 0.017%

    No Known Activations