© 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. 9676
    Prev
    Next
    INDEX
    Explanations

    viral

    np_max-act · gemini-2.0-flash
    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
    åħľ
    -0.28
    人çĶŁ
    -0.26
    åħ¬åħ±åį«çĶŁ
    -0.25
    slack
    -0.25
    éĩį
    -0.24
    .health
    -0.24
    whereIn
    -0.24
    lip
    -0.24
    çļĦ人çĶŁ
    -0.24
     lip
    -0.24
    POSITIVE LOGITS
    讳
    0.28
     æĸ¹æ³ķ
    0.27
    ICES
    0.26
    ãģĿãģĹãģ¦
    0.26
    /method
    0.25
     intensity
    0.24
     inversion
    0.24
    pcs
    0.24
     cur
    0.23
    rie
    0.23
    Activations Density 0.081%

    No Known Activations