© 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. 62693
    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
    ium
    -0.28
    综
    -0.27
    sen
    -0.27
    æĥľ
    -0.25
    ody
    -0.25
    å¨ĥå¨ĥ
    -0.25
    æĭ¨
    -0.25
    ãģķãģĽãģ¦
    -0.25
    ve
    -0.25
    ja
    -0.24
    POSITIVE LOGITS
    abad
    0.32
    afen
    0.32
    ajes
    0.25
    _Field
    0.25
    æŃ·
    0.24
    Constructed
    0.24
    å·§åIJĪ
    0.24
    rimp
    0.24
    viso
    0.24
    USES
    0.24
    Activations Density 15.684%

    No Known Activations

    This feature has no known activations.