© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51808
    Prev
    Next
    INDEX
    Explanations

    describes or specifies

    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
    ovich
    -0.07
    timeofday
    -0.07
     yourself
    -0.07
    让åħ¶
    -0.07
    表çİ°åľ¨
    -0.07
    使å®ĥ
    -0.07
    使åħ¶
    -0.07
    ercial
    -0.07
    åİĨåı²æĸĩåĮĸ
    -0.07
    ä¸Ĭä¸Ģå±Ĥ
    -0.06
    POSITIVE LOGITS
     how
    0.10
    å¦Ĥä½ķéĢļè¿ĩ
    0.10
    çļĦæĺ¯
    0.09
    å¦Ĥä½ķ
    0.09
     cómo
    0.09
    çļĦæĺ¯ä¸Ģ个
    0.09
    å¦Ĥä½ķå°Ĩ
    0.09
     bagaimana
    0.08
    how
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    Activations Density 0.110%

    No Known Activations