© 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. 29726
    Prev
    Next
    INDEX
    Explanations

    confirm that

    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
    å°¤åħ¶æĺ¯
    -0.06
    ä¾Ŀ
    -0.06
    oyo
    -0.06
    iano
    -0.06
    çī¹åĪ«æĺ¯
    -0.06
    Õ®
    -0.06
    ãĥĪãĥ¬
    -0.06
    çĻ»å½ķåIJİ
    -0.06
    SError
    -0.06
    ETY
    -0.06
    POSITIVE LOGITS
     alike
    0.10
    åIJĮä¸Ģ个
    0.09
    çļĦéĥ½æĺ¯
    0.08
    éĥ½ä¸įè¦ģ
    0.08
    éĥ½å¥½
    0.08
    缸åIJĮçļĦ
    0.08
    INGER
    0.08
    åĿĩæĺ¯
    0.08
    ä¸įåIJĮçļĦæĺ¯
    0.08
    keb
    0.07
    Activations Density 0.389%

    No Known Activations