© 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. 131016
    Prev
    Next
    INDEX
    Explanations

    pure

    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
    åĽ°
    -0.33
    haft
    -0.28
     Evidence
    -0.25
    æĽ²
    -0.25
    acco
    -0.25
    itez
    -0.24
    Evidence
    -0.24
    å·²ç»ıåľ¨
    -0.24
    Cur
    -0.24
     CIM
    -0.23
    POSITIVE LOGITS
     Redistributions
    0.29
     treatments
    0.25
     orientations
    0.24
    ÑĥÑĪки
    0.24
     dispersion
    0.23
     ÃŃnd
    0.23
    æĦıä¹īä¸ĬçļĦ
    0.23
     tome
    0.23
    æŸ
    0.23
    Malloc
    0.23
    Activations Density 10.445%

    No Known Activations