© 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. 142778
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    frey
    -0.27
     Phen
    -0.27
    æīĵ交éģĵ
    -0.26
    ä¸ĢåĪĨéĴŁ
    -0.26
    çĴ§
    -0.26
    æķ·
    -0.26
    ä¸Ģäºĭ
    -0.25
    phen
    -0.25
    izable
    -0.25
     individual
    -0.25
    POSITIVE LOGITS
    lias
    0.30
    å°Ŀè¯ķ
    0.26
    AVA
    0.26
    _SWAP
    0.26
    庶
    0.25
    cono
    0.25
     Voc
    0.24
    af
    0.24
    atica
    0.24
    swap
    0.24
    Activations Density 21.057%

    No Known Activations

    This feature has no known activations.