© 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. 90309
    Prev
    Next
    INDEX
    Explanations

    scientific/biological literature

    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
    urn
    -0.27
     trend
    -0.27
    umpt
    -0.26
     Äijình
    -0.26
    çģ«çĥ§
    -0.25
    çĶŁäºİ
    -0.25
    åĢĴ
    -0.24
     eventually
    -0.24
    æĿ¥çļĦ
    -0.23
     Morales
    -0.23
    POSITIVE LOGITS
     toes
    0.31
     toe
    0.28
    ilio
    0.27
    Toe
    0.26
    iaux
    0.26
     grandchildren
    0.25
    SBATCH
    0.24
    èĴ
    0.24
    ÃŃcia
    0.24
    ial
    0.24
    Activations Density 17.952%

    No Known Activations