© 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. 89954
    Prev
    Next
    INDEX
    Explanations

    Numbers and amounts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»İæѤ
    -0.30
    elts
    -0.28
    otp
    -0.28
    æİ¥æīĭ
    -0.26
    cour
    -0.25
    iou
    -0.25
    å¤ĸåĮħ
    -0.25
    inputEmail
    -0.25
    duct
    -0.25
    çļĦä¸Ģ个
    -0.25
    POSITIVE LOGITS
    fram
    0.31
    æĿ¥çľĭçľĭåIJ§
    0.26
    mented
    0.26
     certain
    0.26
     differentiated
    0.25
     phosph
    0.25
    åħį责声æĺİ
    0.24
    ÑĦа
    0.24
    hausen
    0.24
    å¹ħ
    0.24
    Activations Density 8.006%

    No Known Activations