© 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. 14833
    Prev
    Next
    INDEX
    Explanations

    `.version`, `.frame`, `url`, `date`, `Log`

    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
    iesz
    -0.07
    erna
    -0.06
    大åı¯
    -0.06
    overn
    -0.06
    .Cast
    -0.06
    çıĬ
    -0.06
    alo
    -0.06
     Dia
    -0.06
     Samm
    -0.06
    enna
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦ
    0.14
    åIJ«æľīçļĦ
    0.12
    åħ¶ä¸ŃçļĦ
    0.11
    ä¸ŃçļĦéĩįè¦ģ
    0.11
    æīĢåIJ«
    0.10
    ä¸Ńãģ®
    0.10
    å½ĵä¸ŃçļĦ
    0.10
    ãģ«åIJ«ãģ¾
    0.10
    ä¸Ńä¹ĭ
    0.10
    ä¸ŃåIJ«æľī
    0.10
    Activations Density 0.267%

    No Known Activations