© 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. 88241
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    unds
    -0.32
    onds
    -0.32
     sandwiches
    -0.27
    æľīä¸Ģç§į
    -0.25
     affairs
    -0.24
     apar
    -0.24
    istinguished
    -0.24
     wah
    -0.24
    ernes
    -0.24
    angel
    -0.24
    POSITIVE LOGITS
    æ°´å¹³
    0.26
    èģĶéĤ¦
    0.26
    avel
    0.26
    erd
    0.25
     Ãĩa
    0.25
    ory
    0.24
    lush
    0.24
     Federal
    0.24
     IV
    0.24
    ca
    0.24
    Activations Density 76.867%

    No Known Activations