© 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. 9678
    Prev
    Next
    INDEX
    Explanations

    drugs

    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
    aille
    -0.30
    æľīçļĦ
    -0.30
    æŁIJäºĽ
    -0.30
     certain
    -0.29
    ò
    -0.28
     cheers
    -0.28
    rus
    -0.28
    å¤ļæķ°
    -0.27
     inj
    -0.27
    Certain
    -0.27
    POSITIVE LOGITS
    (dot
    0.29
     ypos
    0.29
    çĢļ
    0.27
     vign
    0.27
    ATOM
    0.26
    recogn
    0.25
    .bundle
    0.25
     xls
    0.24
    翳
    0.24
    atom
    0.23
    Activations Density 0.238%

    No Known Activations