© 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. 22-TRANSCODER-HP
    7. 97131
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    blo
    -0.28
    ritis
    -0.27
    å·²ä¹ħ
    -0.26
    ettes
    -0.25
     alike
    -0.24
    mixed
    -0.24
     quickest
    -0.24
    itude
    -0.24
    odal
    -0.24
    GetWidth
    -0.23
    POSITIVE LOGITS
    os
    0.30
    Âł
    0.28
    Newsletter
    0.28
     sal
    0.27
    yt
    0.26
     pro
    0.26
    _
    0.25
    ferred
    0.25
     while
    0.24
     position
    0.24
    Activations Density 0.107%

    No Known Activations

    This feature has no known activations.