© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    medical suffixes

    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
    oc
    -0.08
    apl
    -0.07
    ãĢįãĢģãĢĮ
    -0.07
     oc
    -0.06
     inilah
    -0.06
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    -0.06
    றி
    -0.06
    å©ī
    -0.06
    ocl
    -0.06
    éĥ½åIJĪ
    -0.06
    POSITIVE LOGITS
    yai
    0.07
    биÑı
    0.07
    ceaux
    0.07
    åįİ西
    0.07
    ä½Ļ家
    0.07
    tright
    0.07
    ysteme
    0.07
    åħ·ä½ĵåĨħ容
    0.07
    åı¯èĥ½å¯¼èĩ´
    0.07
    ä¸ŃåĽ½å®¶
    0.07
    Activations Density 1.494%

    No Known Activations