© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108653
    Prev
    Next
    INDEX
    Explanations

    poliovirus

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    åIJĪçIJĨæĢ§
    -0.29
    æĢķ
    -0.27
     software
    -0.26
     rig
    -0.26
    å³Ń
    -0.26
     leveled
    -0.26
     Reflection
    -0.25
    严谨
    -0.25
    icas
    -0.25
    å®īåħ¨æĢ§
    -0.25
    POSITIVE LOGITS
    ç«ĭæĸ¹
    0.28
    /pm
    0.28
    ä¸ĭ车
    0.26
    ¹Ħ
    0.26
    ÅĦsk
    0.25
     deque
    0.25
     Buzz
    0.25
    	Int
    0.25
     REPL
    0.25
    mui
    0.24
    Activations Density 2.268%

    No Known Activations