© 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. 90250
    Prev
    Next
    INDEX
    Explanations

    code files

    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
    wers
    -0.31
    æĥħ人
    -0.29
    åħ¬çĽĬæĢ§
    -0.28
    å¢ŀåĢ¼æľįåĬ¡
    -0.27
    è¾¾åĪ°äºĨ
    -0.26
    oven
    -0.26
    owitz
    -0.25
     GA
    -0.25
    orses
    -0.25
    ä»»ä½ķå½¢å¼ı
    -0.24
    POSITIVE LOGITS
     gri
    0.30
    zion
    0.27
    æ±
    0.25
    羡
    0.25
     emotion
    0.25
    沫
    0.24
    :no
    0.24
     youngest
    0.23
    ä»Ģä¹Īæĺ¯
    0.23
    .Decode
    0.23
    Activations Density 2.086%

    No Known Activations