© 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. 140779
    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
    Atl
    -0.27
    Contrib
    -0.26
     retros
    -0.25
    çĶ¨å¾®ä¿¡
    -0.25
    éĢļ讯åijĺ
    -0.25
    RESULTS
    -0.25
    èĥ¨
    -0.25
    æĴŃ
    -0.24
     Maker
    -0.24
     contributors
    -0.23
    POSITIVE LOGITS
    å¯ĨéĽĨ
    0.27
     Cherry
    0.24
     íķ
    0.24
    еннÑĭе
    0.23
    æķ´ä½ĵ
    0.23
    venes
    0.22
    usta
    0.22
    è°į
    0.22
    è§Ħ
    0.22
     strap
    0.22
    Activations Density 2.093%

    No Known Activations

    This feature has no known activations.