© 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. 42887
    Prev
    Next
    INDEX
    Explanations

    html structure tags or Outlook

    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
    urs
    -0.07
    ãģ¾ãģ¾
    -0.07
    å¤ĸ人
    -0.06
    ær
    -0.06
    çľģçļĦ
    -0.06
    åıĪåĥı
    -0.06
    ¿
    -0.06
     heen
    -0.06
     poco
    -0.06
    ä¸įçĶĺå¿ĥ
    -0.06
    POSITIVE LOGITS
     instead
    0.09
    à¹ģà¸Ĺà¸Ļ
    0.09
    ovich
    0.08
    åıĸèĢĮ代ä¹ĭ
    0.08
    ä¸įåĨįæľī
    0.08
     вмеÑģÑĤо
    0.08
    ä¹Łä¸įåĨį
    0.08
    instead
    0.08
    YC
    0.07
    æ¦Ĥ
    0.07
    Activations Density 0.157%

    No Known Activations