© 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. 15930
    Prev
    Next
    INDEX
    Explanations

    percentage contained

    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
    _java
    -0.07
    æĮīçħ§åĽ½å®¶
    -0.07
    æij©æł¹
    -0.07
     unavoid
    -0.07
    æĪij们æ¯ı个人
    -0.06
    iro
    -0.06
    çİĽçijĻ
    -0.06
    uppy
    -0.06
    undy
    -0.06
     bour
    -0.06
    POSITIVE LOGITS
    פ×Ķ
    0.08
    ä¼ļéĢīæĭ©
    0.07
    zyn
    0.07
    è°ģæĺ¯
    0.07
    zut
    0.07
     accred
    0.07
    å¾ħåĪ°
    0.07
    å®ļäºİ
    0.07
    æIJľéĽĨ
    0.07
    |#
    0.07
    Activations Density 0.355%

    No Known Activations