© 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. 62724
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific documents

    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
    æĬĬå®ĥ
    -0.29
     Material
    -0.27
    çĩ
    -0.27
    .Release
    -0.26
    .Timeout
    -0.25
     tempor
    -0.25
     Gun
    -0.25
    hop
    -0.25
    Temp
    -0.25
     season
    -0.25
    POSITIVE LOGITS
    å¢ŀéĩı
    0.30
    ASSES
    0.26
    zens
    0.26
     unions
    0.26
    æ¯ıä¸Ģ
    0.26
    gems
    0.25
     XCT
    0.25
    hood
    0.25
    cci
    0.25
    鼶ç¢İ
    0.25
    Activations Density 8.165%

    No Known Activations