© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    a following a pattern

    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»»ä½ķåħ¶ä»ĸ
    -0.09
    åįļæĸĩ
    -0.08
    éĢĤå½ĵ
    -0.08
    缸åºĶçļĦ
    -0.08
    éģ©çķ¶
    -0.08
    FML
    -0.08
    ître
    -0.08
    uw
    -0.08
    éĢĤå½ĵçļĦ
    -0.08
    ÅĻe
    -0.07
    POSITIVE LOGITS
    ãģĤãģı
    0.10
    çļĦæĺ¯ä¸Ģ个
    0.08
     relatively
    0.08
     mostly
    0.07
    çļĦéĥ½æĺ¯
    0.07
    人åķĬ
    0.07
    主ãģ«
    0.07
    çļĦæĺ¯
    0.07
    人æĿ¥è¯´
    0.07
    çļĦ人æĿ¥è¯´
    0.07
    Activations Density 0.020%

    No Known Activations