© 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. 19-TRANSCODER-HP
    7. 9400
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¸łéģĵ
    -0.28
    phans
    -0.27
    Cause
    -0.27
     Lage
    -0.27
    cause
    -0.25
    ncy
    -0.25
    UDO
    -0.25
     cause
    -0.24
    ez
    -0.23
    etas
    -0.23
    POSITIVE LOGITS
    åIJĦè¡Į
    0.27
    åĬłåĪĨ
    0.26
    æľīæķĪ
    0.26
     Armstrong
    0.25
    /MPL
    0.24
     autoc
    0.23
    araoh
    0.23
    ︱
    0.22
    arya
    0.22
     stro
    0.22
    Activations Density 0.924%

    No Known Activations

    This feature has no known activations.