© 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. 18771
    Prev
    Next
    INDEX
    Explanations

    into a, into the, relating to, of the, to the

    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
    anski
    -0.08
    ä¸īèĢħ
    -0.07
    äºĮèĢħ
    -0.07
     tudo
    -0.07
    äºĨä¸ĢåĪĩ
    -0.07
    两èĢħ
    -0.07
    onaut
    -0.07
    aille
    -0.07
     everything
    -0.07
     alles
    -0.06
    POSITIVE LOGITS
    æŁIJ个
    0.18
    æŁIJ
    0.17
    æŁIJä¸Ģ个
    0.17
    æŁIJä¸Ģ
    0.16
    æŁIJåĢĭ
    0.16
    åľ¨æŁIJ
    0.14
     particular
    0.12
    æŁIJä¸Ģ天
    0.12
    æŁIJäºĽ
    0.12
    çī¹å®ļãģ®
    0.11
    Activations Density 0.360%

    No Known Activations