© 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. 18-TRANSCODER-HP
    7. 88253
    Prev
    Next
    INDEX
    Explanations

    Medical disorders and diseases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ario
    -0.28
     Saturdays
    -0.27
    ä¸Ģè½®
    -0.26
    åī¯ä¹¦è®°
    -0.25
     Overs
    -0.25
    appendChild
    -0.24
    ucks
    -0.24
    (bottom
    -0.24
    DRAW
    -0.23
    èĪ¸
    -0.23
    POSITIVE LOGITS
    ·¨
    0.25
    nÃŃ
    0.24
     addressed
    0.24
    olec
    0.23
    ient
    0.23
    è¿Ļçīĩ
    0.23
    çĭ±
    0.23
    anza
    0.23
    æ²®
    0.23
    ift
    0.23
    Activations Density 15.122%

    No Known Activations