© 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. 27068
    Prev
    Next
    INDEX
    Explanations

    in each

    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¶äºº
    -0.06
    æĿĤ
    -0.06
    spread
    -0.06
    anak
    -0.06
    Õ£
    -0.06
    arnya
    -0.06
    idik
    -0.06
    nev
    -0.06
    uild
    -0.06
    èįIJ
    -0.06
    POSITIVE LOGITS
     both
    0.17
    both
    0.16
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.15
     beiden
    0.14
     each
    0.14
     обоиÑħ
    0.14
     masing
    0.14
     beide
    0.13
     ambas
    0.13
     BOTH
    0.13
    Activations Density 0.166%

    No Known Activations