© 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. 25747
    Prev
    Next
    INDEX
    Explanations

    variables x and y

    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
    ifte
    -0.09
    баланÑģи
    -0.09
    à¹ģละสà¹Īà¸ĩ
    -0.08
    éĩıåĴĮ
    -0.08
    blr
    -0.08
    AllWindows
    -0.08
    çĻ½éª¨
    -0.08
    미ëĤĺ
    -0.08
    ArrayOf
    -0.08
    untu
    -0.08
    POSITIVE LOGITS
     respectively
    0.15
     alike
    0.14
    åĪĨåĪ«
    0.13
    åĪĨåĪ«æĺ¯
    0.13
    ãģĿãĤĮãģŀãĤĮ
    0.11
    è¿Ļ两个
    0.10
    åĪĨåĪ«ä»İ
    0.10
    åĪĨåĪ«åľ¨
    0.10
    ãģ¨ãĤĤãģ«
    0.10
    åIJĦèĩªçļĦ
    0.10
    Activations Density 0.025%

    No Known Activations