© 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. 30405
    Prev
    Next
    INDEX
    Explanations

    implicit, implied, assumed

    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
    å¤įåIJĪåŀĭ
    -0.07
    á»Ĩ
    -0.07
     indiscrim
    -0.07
    乱象
    -0.07
    akon
    -0.07
    æī°ä¹±
    -0.07
    åı¯çĶ¨äºİ
    -0.06
    éal
    -0.06
    _heap
    -0.06
    ä¸įåĪĨ
    -0.06
    POSITIVE LOGITS
    implicit
    0.14
     implicit
    0.14
     implicitly
    0.13
     Implicit
    0.13
    Implicit
    0.13
    éļIJåIJ«
    0.13
    é»ĺ认
    0.12
    implicitly
    0.12
    ä¸įè¨Ģ
    0.12
    é»ĺ认çļĦ
    0.12
    Activations Density 0.073%

    No Known Activations