© 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. 62826
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical text

    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
    lesi
    -0.26
     auditing
    -0.26
     VS
    -0.26
    æĺĩ
    -0.26
     BT
    -0.25
    bery
    -0.25
    æĶ¾è¿ĩ
    -0.25
    åĶ¤
    -0.24
     lif
    -0.24
     "...
    -0.24
    POSITIVE LOGITS
    addError
    0.26
    elah
    0.26
    matching
    0.25
     asynchronously
    0.25
    itelist
    0.25
    ãģĨãģ¡ãģ«
    0.25
    æ¯Ķäºļ
    0.24
     sÅĤow
    0.24
    igar
    0.24
    Matching
    0.24
    Activations Density 33.913%

    No Known Activations