© 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. 142535
    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
    ationToken
    -0.26
    pine
    -0.26
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.25
    ä¸įäºĨ
    -0.25
    ator
    -0.25
    изаÑĨиÑı
    -0.25
    icamente
    -0.25
    olation
    -0.24
    è§ģ
    -0.24
     pena
    -0.24
    POSITIVE LOGITS
     Ark
    0.26
    heimer
    0.25
    ercul
    0.25
    åĭ¤åĬ³
    0.25
     Adler
    0.25
    CERT
    0.24
     testified
    0.23
    rod
    0.23
    sdk
    0.23
    alk
    0.23
    Activations Density 22.976%

    No Known Activations

    This feature has no known activations.