© 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. 108636
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    çĶŁäº§è®¾å¤ĩ
    -0.26
    jest
    -0.26
    rão
    -0.25
     oscill
    -0.25
    agram
    -0.24
     sake
    -0.24
    å®ħ
    -0.24
    ideo
    -0.24
     PDO
    -0.24
     distr
    -0.23
    POSITIVE LOGITS
    åı¯èĥ½æĢ§
    0.26
    å¤ļä½į
    0.25
    æIJº
    0.25
    клÑİÑĩа
    0.24
     resultado
    0.24
    [--
    0.24
    odont
    0.24
    utzer
    0.24
     remot
    0.23
     både
    0.23
    Activations Density 0.139%

    No Known Activations