© 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. 13874
    Prev
    Next
    INDEX
    Explanations

    code delimiters and symbols

    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
    管æīĢ
    -0.07
    ÙĪÙī
    -0.07
    ongs
    -0.07
    ä½įåľ¨
    -0.07
     {_
    -0.07
    åĩºåħ¶
    -0.07
    å¥½åľ¨
    -0.07
    ä¿Ŀæľī
    -0.06
    è´¹çĶ¨çĶ±
    -0.06
    éĽĨåħ¨
    -0.06
    POSITIVE LOGITS
    adu
    0.07
     инÑĤен
    0.07
    anka
    0.07
    à¸Ĩ
    0.06
    身æĹģçļĦ
    0.06
     اÙĦÙħØ·
    0.06
     Virtu
    0.06
    глÑı
    0.06
    acker
    0.06
     ISI
    0.06
    Activations Density 0.015%

    No Known Activations