© 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. 142746
    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
     freeze
    -0.28
    mania
    -0.26
     widow
    -0.26
    çµĤæĸ¼
    -0.25
     producers
    -0.25
    è½®
    -0.25
    wagon
    -0.25
    ipel
    -0.25
     Freeze
    -0.25
    ç»Īäºİ
    -0.25
    POSITIVE LOGITS
    FAQ
    0.26
     autoload
    0.25
    significant
    0.25
    lasting
    0.24
    amax
    0.24
    å°ijåIJĥ
    0.24
    åħijçİ°
    0.24
    (ax
    0.23
    [max
    0.23
    obs
    0.23
    Activations Density 0.089%

    No Known Activations

    This feature has no known activations.