© 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. 129164
    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
    è·ĭ
    -0.26
    çĦī
    -0.26
     analytic
    -0.26
    çªŁ
    -0.25
    arnation
    -0.25
    åĶ®åįĸ
    -0.25
    é¼»åŃIJ
    -0.24
    è´¨
    -0.24
    亲
    -0.23
    oload
    -0.23
    POSITIVE LOGITS
    uxt
    0.26
     concepts
    0.26
    nergy
    0.24
    elle
    0.24
    ao
    0.24
    rogram
    0.24
    NE
    0.24
    lle
    0.23
    Featured
    0.23
     concept
    0.23
    Activations Density 0.068%

    No Known Activations

    This feature has no known activations.