© 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. 14-TRANSCODER-HP
    7. 41742
    Prev
    Next
    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -league
    -0.30
    ctal
    -0.28
    tsky
    -0.28
    nts
    -0.27
    Transactional
    -0.27
    à´´
    -0.27
    arser
    -0.27
    idan
    -0.26
    atrice
    -0.26
    Netflix
    -0.26
    POSITIVE LOGITS
    @g
    0.28
    çŨ
    0.27
    outh
    0.27
    ä¸Ńåįİ人æ°ij
    0.25
    ))))
    0.24
     corner
    0.24
    corn
    0.23
    ank
    0.23
     Poz
    0.23
     Rust
    0.23
    Activations Density 0.036%

    No Known Activations