© 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. 64841
    Prev
    Next
    INDEX
    Explanations

    determining value/worthiness

    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
    å°Ķæĸ¯
    -0.27
     caves
    -0.26
     tunnels
    -0.26
    éķ¶åµĮ
    -0.25
    ectors
    -0.25
    avn
    -0.24
    iena
    -0.24
    çļĦ大
    -0.24
    aption
    -0.24
     vacuum
    -0.24
    POSITIVE LOGITS
    è¯ļæĦı
    0.30
    常æĢģ
    0.26
    åĵ¥
    0.25
    -serif
    0.25
    -Requested
    0.25
    aub
    0.24
    uffled
    0.24
    ä¸¥æł¼æī§è¡Į
    0.24
    第ä¸Ģ次
    0.24
     darling
    0.24
    Activations Density 14.244%

    No Known Activations