© 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. 60316
    Prev
    Next
    INDEX
    Explanations

    index or position

    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
    =ax
    -0.08
    æ£ĢæŁ¥ç»Ħ
    -0.07
     stress
    -0.07
     Stress
    -0.07
    REAM
    -0.06
    anagan
    -0.06
    irim
    -0.06
    æīĽ
    -0.06
    =back
    -0.06
    .Values
    -0.06
    POSITIVE LOGITS
    ä½įç½®
    0.10
    ä½įç½®çļĦ
    0.10
    ä½įç½®ä¸Ĭ
    0.10
    <usize
    0.09
    ç´¢å¼ķ
    0.09
     positions
    0.09
     позиÑĨии
    0.08
    skar
    0.08
     ìľĦì¹ĺ
    0.08
    à¸ķำà¹ģหà¸Ļà¹Īà¸ĩ
    0.08
    Activations Density 0.082%

    No Known Activations