© 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. 9-TRANSCODER-HP
    7. 29288
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ndl
    -0.25
     *(*
    -0.25
    (DBG
    -0.25
     gim
    -0.24
    LOPT
    -0.24
    .dim
    -0.24
    uding
    -0.24
     Nat
    -0.23
    /lgpl
    -0.23
    Dim
    -0.23
    POSITIVE LOGITS
    oni
    0.26
    nip
    0.26
    修为
    0.25
    ant
    0.25
     bin
    0.25
    owns
    0.25
    bin
    0.24
    âĸIJ
    0.24
    ania
    0.24
    -doc
    0.23
    Activations Density 0.256%

    No Known Activations

    This feature has no known activations.