© 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. 64866
    Prev
    Next
    INDEX
    Explanations

    Programming bugs / issues

    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
    é©·
    -0.26
    为æ°ij
    -0.25
    loit
    -0.24
     Def
    -0.24
     bas
    -0.24
    sher
    -0.24
    è¿ĻäºĽéĹ®é¢ĺ
    -0.24
     por
    -0.24
    ä¹ī
    -0.24
     POR
    -0.24
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.26
    廳
    0.25
     hut
    0.25
    NY
    0.25
    ursday
    0.24
    缸éģĩ
    0.24
    ql
    0.24
    isms
    0.24
     runnable
    0.24
    :{}
    0.24
    Activations Density 3.423%

    No Known Activations