© 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. 30054
    Prev
    Next
    INDEX
    Explanations

    legal document beginnings

    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
    çĶŁæĦı
    -0.07
    ynch
    -0.07
    anmar
    -0.07
    å°½å¿ĥå°½åĬĽ
    -0.07
    å°Ĭ
    -0.06
     affront
    -0.06
    æĺ¯ä¸Ģ款
    -0.06
    اÙĦÙī
    -0.06
    ä»·éĴ±
    -0.06
    ÑĪенÑĮ
    -0.06
    POSITIVE LOGITS
    orney
    0.08
    itzer
    0.07
    czy
    0.07
    代è¡Į
    0.06
    ç¼Ģ
    0.06
    edException
    0.06
    lipp
    0.06
    icus
    0.06
     Moo
    0.06
    lessness
    0.06
    Activations Density 0.008%

    No Known Activations