© 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. 9690
    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
    人æ°ij
    -0.26
    åĽ´
    -0.26
    rias
    -0.26
    çļĦåį°è±¡
    -0.26
    Slug
    -0.25
    ents
    -0.25
    åĪ®
    -0.24
    ilio
    -0.24
     permanent
    -0.24
    ä¸įç¡®å®ļ
    -0.24
    POSITIVE LOGITS
     alike
    0.30
    anut
    0.29
    adem
    0.26
    ť
    0.25
    ambi
    0.25
    ades
    0.25
    ä¼¼
    0.25
    槽
    0.25
    æ²®
    0.24
    vore
    0.24
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.