© 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. 17035
    Prev
    Next
    INDEX
    Explanations

    receiving or incoming data

    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
    åĩºæĿ¥äºĨ
    -0.07
    TERN
    -0.07
    ļľ
    -0.07
    بÙĤ
    -0.07
    èħ¾è®¯å¾®åįļ
    -0.07
    éĻIJåĪ¶åĩºå¢ĥ
    -0.07
    ardt
    -0.07
    aunch
    -0.07
    pedia
    -0.07
    ekar
    -0.06
    POSITIVE LOGITS
    æİ¥æĶ¶
    0.17
     reception
    0.15
     receiving
    0.14
     réception
    0.14
     Reception
    0.13
     receipt
    0.13
     incoming
    0.13
     received
    0.13
     Receive
    0.13
    .receive
    0.13
    Activations Density 0.253%

    No Known Activations