© 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. 129315
    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
    _acl
    -0.28
    ESA
    -0.28
     administr
    -0.27
    administrator
    -0.27
     materiaÅĤ
    -0.26
     administer
    -0.25
    essional
    -0.25
     olu
    -0.25
    é»ijèī²
    -0.25
    pq
    -0.25
    POSITIVE LOGITS
    zier
    0.28
    积æŀģåĵįåºĶ
    0.27
    omed
    0.27
     thresh
    0.26
     Little
    0.25
    çł£
    0.24
    ç»ĻåĬĽ
    0.24
    arget
    0.24
    wargs
    0.24
    çīĪ
    0.24
    Activations Density 4.325%

    No Known Activations

    This feature has no known activations.