© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    list item characters

    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
    çĿ
    -0.08
    gin
    -0.07
     Zimmerman
    -0.06
    irk
    -0.06
     Stanton
    -0.06
    åľ¨è·¯ä¸Ĭ
    -0.06
    .getContext
    -0.06
     Gregory
    -0.06
    gay
    -0.06
    èŀįèŀį
    -0.06
    POSITIVE LOGITS
    ÙĪÙĨÙĩ
    0.07
    éľ²
    0.07
    ucene
    0.07
    天çĽĸ
    0.07
    å¹Į
    0.07
    uccio
    0.06
    à¸ŀัà¸Ļà¸ĺุà¹Į
    0.06
    odus
    0.06
     Ones
    0.06
    å©·
    0.06
    Activations Density 0.014%

    No Known Activations