© 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. 64286
    Prev
    Next
    INDEX
    Explanations

    proper names and following words

    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
    ئة
    -0.07
    èĩ³å°ijæľī
    -0.06
    intendent
    -0.06
    åĽŃéķ¿
    -0.06
    åĴĮæľī
    -0.06
    omore
    -0.06
    _provider
    -0.06
    veral
    -0.06
    å°½éĩı
    -0.06
    éĤ£é¢Ĺ
    -0.06
    POSITIVE LOGITS
     Stéph
    0.08
    ä¸Ģç»ı
    0.08
    roje
    0.08
    å·²ä¹ħçļĦ
    0.07
    äºĨæĮĩ
    0.07
    ä¹ĭåĽ½
    0.07
    chè
    0.07
    ç½ijç«Ļåľ°åĽ¾
    0.07
    _partitions
    0.07
    pNet
    0.07
    Activations Density 0.869%

    No Known Activations