© 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. 108786
    Prev
    Next
    INDEX
    Explanations

    documentation/specifications

    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
    anka
    -0.26
    åħ¨åľº
    -0.26
    èģĶç½ij
    -0.26
     BUFF
    -0.25
    æīĢè¬Ĥ
    -0.24
     revolver
    -0.24
    .Bytes
    -0.24
    èģ²
    -0.23
    IÃĬ
    -0.23
     Buff
    -0.23
    POSITIVE LOGITS
    æĢ¥éľĢ
    0.29
     Asked
    0.26
     ecology
    0.26
    vj
    0.26
    TabPage
    0.26
    çĶŁæĢģ
    0.26
     ecological
    0.25
    壮
    0.25
     paddle
    0.25
     padd
    0.25
    Activations Density 11.966%

    No Known Activations