© 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. 64884
    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
    ingly
    -0.28
    .failure
    -0.27
    ãĥ¯ãĥ¼ãĤ¯
    -0.26
    /how
    -0.25
     Mush
    -0.25
    artial
    -0.25
    osten
    -0.25
     useClass
    -0.24
    oral
    -0.24
    ocities
    -0.24
    POSITIVE LOGITS
    éĽĨä¸Ńåľ¨
    0.29
    åĪĨæķ£
    0.28
    éĿł
    0.28
    æ·¡åĮĸ
    0.26
     softer
    0.25
    anned
    0.25
    mony
    0.25
    ç©¿ä¸Ĭ
    0.25
     corruption
    0.24
    ide
    0.24
    Activations Density 0.239%

    No Known Activations

    This feature has no known activations.