© 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. 39422
    Prev
    Next
    INDEX
    Explanations

    technical/descriptive passages

    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
    eldo
    -0.26
     neutrality
    -0.26
    neutral
    -0.25
    .ease
    -0.25
    ellation
    -0.25
    agnostic
    -0.24
    ç·©
    -0.24
    Ợ
    -0.24
    -neutral
    -0.24
     newsletter
    -0.23
    POSITIVE LOGITS
    Cy
    0.28
    ISM
    0.27
    FR
    0.25
    Dom
    0.25
    è´Łè´£
    0.25
     Brother
    0.25
    xmm
    0.25
    åIJ¬è¯¾
    0.25
    owo
    0.24
    ix
    0.24
    Activations Density 0.213%

    No Known Activations