© 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. 33-TRANSCODER-HP
    7. 54560
    Prev
    Next
    INDEX
    Explanations

    Medical/pharmaceutical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åľ£
    -0.28
    gf
    -0.28
    vä
    -0.26
    tica
    -0.26
    è¯į
    -0.25
    çĤ¹
    -0.25
     æµ
    -0.25
    æ¦ĸ
    -0.24
    olis
    -0.24
    ucks
    -0.24
    POSITIVE LOGITS
    à¸ģรรม
    0.30
    æĭĶ
    0.28
    itarian
    0.27
    rial
    0.26
    icie
    0.26
     prescription
    0.26
     substr
    0.25
    çı¥
    0.24
     perks
    0.24
    导åIJij
    0.23
    Activations Density 0.011%

    No Known Activations