© 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. 55990
    Prev
    Next
    INDEX
    Explanations

    job titles and professionals

    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
    åħ¬åı¸èij£äºĭéķ¿
    -0.08
    é¢Ĩè¢ĸ
    -0.08
    åħ¬ä¼Ĺå¹³åı°
    -0.07
    adem
    -0.07
    é¢Ĩ导人
    -0.07
     encom
    -0.07
    æµ·åĨħå¤ĸ
    -0.07
    beste
    -0.07
    katan
    -0.07
    ple
    -0.07
    POSITIVE LOGITS
    ä¸ĵéŨ
    0.11
    ä¸ĵéŨçļĦ
    0.10
    ä¸ĵçĶ¨çļĦ
    0.09
    è´Łè´£å¯¹
    0.09
     dedicated
    0.09
    è´Łè´£
    0.09
    ä¸ĵçĶ¨
    0.09
     specialist
    0.09
     responsible
    0.08
    å°ĪéĸĢ
    0.08
    Activations Density 0.196%

    No Known Activations