© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    data encoding and conversion

    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
    åĽŀæĿ¥
    -0.08
    å½ĴæĿ¥
    -0.07
    åĽŀä¾Ĩ
    -0.07
    razier
    -0.07
    erman
    -0.07
    åĽŀæĿ¥äºĨ
    -0.07
    ä½įç½®ä¸Ĭ
    -0.07
     colspan
    -0.07
     inher
    -0.07
    æ©¡
    -0.07
    POSITIVE LOGITS
    åĩĨå¤ĩ好çļĦ
    0.09
    ToSend
    0.09
    Encoded
    0.07
    Convertible
    0.07
     prepared
    0.07
    .convert
    0.07
     Encrypt
    0.07
    åĨħå®¹è¿Ľè¡Į
    0.07
    å¯Ĩå°ģ
    0.07
    åĩĨå¤ĩ
    0.07
    Activations Density 0.532%

    No Known Activations