© 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. 18-TRANSCODER-HP
    7. 90139
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     MOST
    -0.27
     NEG
    -0.26
    äºıæįŁ
    -0.26
     RETURNS
    -0.25
     Singles
    -0.25
    丢
    -0.24
     losers
    -0.24
    ibile
    -0.24
     Negative
    -0.24
    峪
    -0.24
    POSITIVE LOGITS
     Locker
    0.28
    åı¯æĥ³èĢĮçŁ¥
    0.26
     worn
    0.25
    æľºæŀĦ
    0.25
    mandatory
    0.24
     subtitle
    0.24
     readline
    0.24
     tÃŃn
    0.24
    ä¸įåı¯éģ¿åħį
    0.24
    aption
    0.23
    Activations Density 17.505%

    No Known Activations