© 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. 90348
    Prev
    Next
    INDEX
    Explanations

    mixed content text

    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
    illos
    -0.28
    <![
    -0.28
    ocide
    -0.28
    好äºĨ
    -0.25
     Corm
    -0.25
    çĬ¬
    -0.25
    osity
    -0.25
    erate
    -0.24
    xford
    -0.24
    splice
    -0.24
    POSITIVE LOGITS
    LEY
    0.26
    UDA
    0.26
    é«ĺä»·
    0.25
    (Syntax
    0.25
    ULE
    0.25
    leta
    0.25
    azi
    0.24
    uda
    0.24
    hu
    0.24
    lg
    0.23
    Activations Density 3.715%

    No Known Activations