© 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. 56579
    Prev
    Next
    INDEX
    Explanations

    making friends and social connections

    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
    ear
    -0.07
    äºĮ人çļĦ
    -0.07
    两人
    -0.07
    åıĹçIJĨ
    -0.07
    éĩįä¸Ńä¹ĭéĩį
    -0.07
    æİĪæĿĥ使çĶ¨
    -0.06
     disputed
    -0.06
    为人æ°ij
    -0.06
    人人éĥ½
    -0.06
    oval
    -0.06
    POSITIVE LOGITS
     camar
    0.12
    å¿ĹåIJĮéģĵåIJĪ
    0.11
     fellow
    0.11
    å½¼æѤ
    0.10
    çļĦåIJĮ
    0.10
    æľĭ
    0.09
     sesama
    0.09
     networking
    0.09
     Fellow
    0.09
    åIJĮé¾Ħ
    0.09
    Activations Density 0.387%

    No Known Activations