© 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. 47971
    Prev
    Next
    INDEX
    Explanations

    Hungarian word endings

    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
    æĺŃ
    -0.07
    tot
    -0.06
    åłĤåłĤ
    -0.06
    inga
    -0.06
    å¾IJå¾IJ
    -0.06
    æĺ¥åįİ
    -0.06
    [result
    -0.06
     SK
    -0.06
     bottom
    -0.06
    éĽ£
    -0.06
    POSITIVE LOGITS
    eder
    0.09
    å¤§ä½ľ
    0.08
    erver
    0.08
    .Yes
    0.08
     feas
    0.08
    Ðijе
    0.08
    éch
    0.08
    å¾Īæĺİæĺ¾
    0.08
    ceg
    0.07
    “Yes
    0.07
    Activations Density 0.065%

    No Known Activations