© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63446
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ded
    -0.29
    rem
    -0.27
    ope
    -0.27
    est
    -0.27
    \")
    -0.26
     herr
    -0.26
    eth
    -0.26
    нак
    -0.26
    avis
    -0.26
     jack
    -0.26
    POSITIVE LOGITS
     banning
    0.27
     zones
    0.26
    NetMessage
    0.25
    æ»ĭ润
    0.25
     Seats
    0.25
     bach
    0.25
     LSM
    0.24
     leased
    0.24
     ban
    0.23
    (Event
    0.23
    Activations Density 69.622%

    No Known Activations

    This feature has no known activations.