© 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. 28587
    Prev
    Next
    INDEX
    Explanations

    user equipment, terminal, client

    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
     verdient
    -0.07
    æĹłæĦ§
    -0.07
    utherland
    -0.07
    å¼ķè¿ĽäºĨ
    -0.07
     hins
    -0.07
    ä¸Ģåĭº
    -0.07
    embe
    -0.07
    Ùİض
    -0.07
    èķ´åIJ«
    -0.06
    otate
    -0.06
    POSITIVE LOGITS
    æł¹æį®èĩªèº«
    0.09
    端çļĦ
    0.08
     negotiating
    0.08
    åıijåĩºçļĦ
    0.08
     fil
    0.08
    ietta
    0.08
    æĬ¥éĢģ
    0.07
    è¿Ķæł¡
    0.07
     capable
    0.07
    -side
    0.07
    Activations Density 0.178%

    No Known Activations