© 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. 27876
    Prev
    Next
    INDEX
    Explanations

    example, would return

    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
    åıĪä»İ
    -0.07
     ÑĥкÑĥ
    -0.07
    Ord
    -0.07
    è¹ĭ
    -0.07
    ymm
    -0.06
    è´Ŀåħĭ
    -0.06
    uard
    -0.06
    æ¨ĭ
    -0.06
    çļĦç¨ĭ度
    -0.06
    rance
    -0.06
    POSITIVE LOGITS
    à¸Ļิ
    0.08
    acao
    0.06
    便æľī
    0.06
    ä¹°ä¸ĭ
    0.06
     Delicious
    0.06
    .construct
    0.06
    itik
    0.06
    éĩijéĴĪ
    0.06
    annot
    0.06
    ugh
    0.06
    Activations Density 0.022%

    No Known Activations