© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鸾
    -0.31
     COPYRIGHT
    -0.31
    Disposition
    -0.30
    .expect
    -0.29
    	Copyright
    -0.28
    çł»
    -0.27
    singular
    -0.26
    bsite
    -0.26
    oped
    -0.26
     reckon
    -0.26
    POSITIVE LOGITS
    æŁĶåĴĮ
    0.27
     tiết
    0.27
     mess
    0.27
    è´§å¸ģ
    0.25
    æ±Ĺæ°´
    0.24
     glance
    0.24
    ude
    0.24
     periodically
    0.24
    弥漫
    0.23
     crisp
    0.23
    Activations Density 0.455%

    No Known Activations

    This feature has no known activations.