© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    East Hennepin

    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
    ä¸Ĭå½ĵ
    -0.07
    ä¸Ĭ书
    -0.07
    ÃŃvar
    -0.06
    eces
    -0.06
    çļĦæĪIJ绩
    -0.06
     protagon
    -0.06
    å¾Ĺä¸Ģ
    -0.06
    ÙĬØ·
    -0.06
    ç¿ĺ
    -0.06
     ]).
    -0.06
    POSITIVE LOGITS
    ترÙħ
    0.08
     kie
    0.07
    è¶
    0.07
    umm
    0.06
    inn
    0.06
    tot
    0.06
    ç¯ĩäºĮ
    0.06
    ãģ¥
    0.06
    èķī
    0.06
    ÙĨÙĬÙĨ
    0.06
    Activations Density 0.283%

    No Known Activations