© 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. 12097
    Prev
    Next
    INDEX
    Explanations

    weeks pregnant

    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
    ovsky
    -0.07
    unan
    -0.07
    æīĢæľª
    -0.07
    åį³ä»¥
    -0.06
    /non
    -0.06
    fos
    -0.06
     Uncomment
    -0.06
    ä¹ĸå·§
    -0.06
    ning
    -0.06
    æ¹ĺæ±Ł
    -0.06
    POSITIVE LOGITS
    envir
    0.08
    åѦéĩij
    0.07
    áĢŃáĢ¯áĢ¸
    0.07
    .Sdk
    0.07
    è¡£èįī
    0.07
     appunto
    0.07
    yce
    0.07
    angkit
    0.07
    çī
    0.07
     revan
    0.07
    Activations Density 3.079%

    No Known Activations