© 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. 20361
    Prev
    Next
    INDEX
    Explanations

    legal advice

    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
    ppo
    -0.08
    å¡«
    -0.07
    åı°å±±
    -0.07
    gesund
    -0.07
    ekk
    -0.07
    åģļ
    -0.06
    çĶļèĩ³æ¯Ķ
    -0.06
    amal
    -0.06
    æľ¬æĸĩ为åįļ主
    -0.06
    pill
    -0.06
    POSITIVE LOGITS
    ourt
    0.09
    ä¸įè´¥
    0.08
    缸åħ³æ³ķå¾ĭ
    0.07
    缸åħ³æĥħåĨµ
    0.07
    ÙĪرÙĩ
    0.07
    æī¬å¸Ĩ
    0.07
    ç«ŀ
    0.07
    缸ä¾Ŀ
    0.07
    uny
    0.07
    obuf
    0.07
    Activations Density 0.002%

    No Known Activations