© 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. 7386
    Prev
    Next
    INDEX
    Explanations

    both

    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
    onale
    -0.07
    èĤ©ä¸Ĭ
    -0.07
     soph
    -0.06
    onet
    -0.06
    èµ·æºIJ
    -0.06
    าà¸Ļุ
    -0.06
    èµ·è·ij
    -0.06
    对äºİéĤ£äºĽ
    -0.06
     sill
    -0.06
    æľµæľµ
    -0.06
    POSITIVE LOGITS
     both
    0.19
    both
    0.19
     BOTH
    0.16
    Both
    0.16
     zowel
    0.16
     både
    0.15
     Both
    0.15
    æĹ¢æĺ¯
    0.14
    à¸Ĺัà¹īà¸ĩ
    0.14
     sowohl
    0.14
    Activations Density 0.892%

    No Known Activations