© 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. 24085
    Prev
    Next
    INDEX
    Explanations

    selection bias, imbalance, representative sample

    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
    klen
    -0.07
    motion
    -0.07
     convention
    -0.07
     motion
    -0.07
    _motion
    -0.07
    亮
    -0.07
     rắn
    -0.07
    primer
    -0.07
    eroon
    -0.07
    à¹Īà¸ĩ
    -0.07
    POSITIVE LOGITS
    Random
    0.08
    Selection
    0.08
     Random
    0.08
    éļıæľº
    0.08
     assumptions
    0.07
     random
    0.07
    selection
    0.07
     Selection
    0.07
     bias
    0.07
    arz
    0.07
    Activations Density 0.012%

    No Known Activations