© 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. 63561
    Prev
    Next
    INDEX
    Explanations

    code snippet help

    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
    irement
    -0.07
    à¦ł
    -0.07
    äºĨ解ä¸Ģä¸ĭ
    -0.06
    éľĢè¦ģèĢĥèĻij
    -0.06
    æĭĽæĥ¹
    -0.06
     mé
    -0.06
    赤å£ģ
    -0.06
    åı«å¥½
    -0.06
    ä¸Ģ鸣
    -0.06
    äºĨ解ä¸Ģä¸ĭåIJ§
    -0.06
    POSITIVE LOGITS
     exposition
    0.08
    ç¯ĩå¹ħ
    0.08
    欣
    0.07
     simplific
    0.07
    à¸Ľà¸¹
    0.07
    _succ
    0.07
    sert
    0.07
     reproduce
    0.07
     semiclassical
    0.07
    æīĢå±ķ示
    0.07
    Activations Density 0.002%

    No Known Activations