© 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. 90116
    Prev
    Next
    INDEX
    Explanations

    general concepts

    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
    NAS
    -0.27
    åIJĥå¾Ĺ
    -0.25
    tas
    -0.24
    sd
    -0.24
    <small
    -0.23
    sville
    -0.23
    mans
    -0.23
    uess
    -0.23
    ASON
    -0.23
    ñas
    -0.23
    POSITIVE LOGITS
    èĦ±
    0.27
    åĬ¨æľº
    0.25
    软
    0.25
     cÆ°
    0.25
    ,copy
    0.24
    soft
    0.24
    æŀģ
    0.23
    unda
    0.23
    åħ¨éķĩ
    0.23
    ä¾Ľ
    0.23
    Activations Density 29.345%

    No Known Activations