© 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. 24346
    Prev
    Next
    INDEX
    Explanations

    trigger event

    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
    liness
    -0.09
    osis
    -0.08
    eland
    -0.07
    icali
    -0.07
     chá»Ĺ
    -0.07
    åı£éķĩ
    -0.07
    ìŀIJ리
    -0.07
     halnya
    -0.07
    /IP
    -0.07
    iosis
    -0.07
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.09
    æĸ°ä¸Ģè½®
    0.08
    äºĨä¸Ģåľº
    0.08
    ä¸Ģç³»åĪĹ
    0.08
    çľ¼å¸ĺ
    0.08
    并å®ĮæĪIJ
    0.08
    AndWait
    0.08
    éĺµéĺµ
    0.08
    à¹ĥหà¹īà¹Ģà¸ģิà¸Ķ
    0.08
    acte
    0.08
    Activations Density 0.126%

    No Known Activations