© 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. 9646
    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
    Negative Logits
    tls
    -0.30
    ären
    -0.28
    OTA
    -0.27
    venues
    -0.26
    subscriptions
    -0.25
    hé
    -0.25
    oster
    -0.24
     pursue
    -0.24
    caster
    -0.24
     learned
    -0.24
    POSITIVE LOGITS
    è¿Ļ两个
    0.26
    pecific
    0.26
    maid
    0.25
    æ¯Ķè¾ĥç®Ģåįķ
    0.23
    æĭ¢
    0.23
    mans
    0.23
     ArgumentNullException
    0.23
    .root
    0.23
    ä»ħ
    0.23
    maids
    0.23
    Activations Density 1.337%

    No Known Activations

    This feature has no known activations.