© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    category and country names

    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
    ...
    -0.09
     ...
    -0.09
    -0.06
    1
    -0.06
    âĢ¦
    -0.06
     âĢ¦
    -0.06
    åIJ«
    -0.06
    ....
    -0.06
    å°Ĭ
    -0.06
    M
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.12
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.10
    estu
    0.10
    尾声
    0.09
    è½°è½°
    0.09
    жÑĮ
    0.09
    踵
    0.09
    è¯ķçİ©
    0.09
    è¿ĻäºĽäºĭ
    0.09
    /cop
    0.09
    Activations Density 0.001%

    No Known Activations