© 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. 131157
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
     barg
    -0.29
    gies
    -0.28
     Äijá»Ŀi
    -0.26
    ek
    -0.25
    çļĦä½ľåĵģ
    -0.24
     Visual
    -0.24
    ekte
    -0.24
    prés
    -0.24
    åĽ´è§Ĥ
    -0.24
    Visual
    -0.23
    POSITIVE LOGITS
    梵
    0.27
     distinguishing
    0.26
    ÅŁtir
    0.25
    æĪ¾
    0.24
    樾
    0.24
    OLID
    0.24
    azole
    0.24
    è¾į
    0.23
    abor
    0.23
    éģ¿å¼Ģ
    0.23
    Activations Density 7.031%

    No Known Activations