© 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. 49797
    Prev
    Next
    INDEX
    Explanations

    true if

    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
    ä½łåıĪ
    -0.07
    ature
    -0.07
    çĶµæºIJ线
    -0.07
    onato
    -0.07
    viste
    -0.06
    大éĥ¨ä»½
    -0.06
    iman
    -0.06
    ands
    -0.06
    ä½łè¿Ļæĺ¯
    -0.06
    orgia
    -0.06
    POSITIVE LOGITS
     whenever
    0.10
    æĹ¶è¡¨ç¤º
    0.08
    代表
    0.08
    å¦Ĥæŀľè§īå¾Ĺ
    0.08
    åıįæĺłåĩº
    0.08
    enever
    0.08
     wherever
    0.08
    izr
    0.07
     signify
    0.07
     Whenever
    0.07
    Activations Density 0.135%

    No Known Activations